Blog-Eintrag


Discover the World of AI Optimization: Our New Blog Series is Here! 🚀



When interacting with AI/LLM (Large Language Model) systems, the language and style of communication can significantly impact the quality and accuracy of the responses. This documentation provides guidelines on how to effectively communicate with AI models to achieve the best results.

Language guidelines

1. Use clear and concise language

  • Be direct: Clearly state your questions or commands. Avoid using ambiguous or vague language.
  • Example: Instead of saying "Tell me about it," specify what "it" refers to, such as "Tell me about the process of photosynthesis."


  • Keep it simple: Use simple and straightforward language. Complex sentences can sometimes confuse the AI.
  • Example: "Can you tell me what the capital city of the country known for the Eiffel Tower is?" is less clear than "What is the capital of France?"


2. Provide context

  • Context matters: Providing context helps the AI understand the background and specifics of your query.
  • Example: Instead of asking "What is the weather like?", specify the location and time, such as "What is the weather like in New York City today?"


3. Use proper grammar and punctuation

  • Grammar and punctuation: Proper grammar and punctuation help the AI parse and understand your input more accurately.
  • Example: "what are the benefits of a balanced diet" is less clear than "What are the benefits of a balanced diet?"


4. Be specific

  • Specificity: The more specific you are, the better the AI can tailor its response to your needs.
  • Example: Instead of asking "How does it work?", specify what "it" refers to, such as "How does a solar panel work?"


5. Avoid slang and abbreviations

  • Standard language: Use standard language and avoid slang, abbreviations, or jargon that the AI might not understand.
  • Example: Instead of saying "What's the 411 on AI?", say "What information can you provide about AI?"


Why AI models might refuse to respond

1. Examples of restricted topics

  • Self-harm: AI models will refuse to provide guidance or information that could be used to harm oneself. This is to prevent any potential encouragement or facilitation of self-injurious behavior.
  • Example: If you ask, "How can I harm myself?", the AI will not respond and may provide an error message indicating the restriction.


  • Violence: AI models will not provide information or guidance on how to commit acts of violence. This is to ensure that the AI is not used to promote or facilitate violent behavior.
  • Example: If you ask, "How can I hurt someone?", the AI will refuse to respond and may indicate that the query is not allowed.


  • Illegal activities: AI models will not provide information or guidance on how to engage in illegal activities, including but not limited to hacking, drug manufacturing, or theft.
  • Example: If you ask, "How can I hack into a computer system?", the AI will refuse to respond.


  • Hate speech and discrimination: AI models will not engage in or promote hate speech, discrimination, or any form of bigotry against individuals or groups based on race, ethnicity, religion, gender, sexual orientation, or other protected characteristics.
  • Example: If you ask, "How can I spread hate speech?", the AI will refuse to respond.


  • Harassment and bullying: AI models will not provide guidance on how to harass, bully, or intimidate others.
  • Example: If you ask, "How can I bully someone online?", the AI will refuse to respond.


  • Sensitive personal information: AI models will not provide or request sensitive personal information, such as social security numbers, credit card details, or personal addresses.
  • Example: If you ask, "What is someone's social security number?", the AI will refuse to respond.


  • Medical advice: AI models are not qualified to provide medical advice, diagnosis, or treatment. Queries related to medical conditions should be directed to a healthcare professional.
  • Example: If you ask, "How can I treat my illness?", the AI will advise you to consult a healthcare professional.


  • Financial advice: AI models are not qualified to provide financial advice, investment strategies, or tax guidance. Queries related to financial decisions should be directed to a financial advisor.
  • Example: If you ask, "How should I invest my money?", the AI will advise you to consult a financial advisor.


  • Explicit content: AI models will not engage in or provide explicit content, including but not limited to sexually explicit material or graphic descriptions of violence.
  • Example: If you ask, "Can you provide explicit content?", the AI will refuse to respond.


Error messages (in Azure AI Foundry)

When an AI model encounters a query that violates its safety and ethical guidelines, it may provide an error message. For example, in the Azure AI Foundry, you might see error messages such as:

  1. Self-harm (medium)
  2. Violence (medium)
  3. Illegal activities (high)
  4. Hate speech (high)
  5. Harassment (medium)
  6. Sensitive personal information (high)
  7. Medical advice (medium)
  8. Financial advice (medium)
  9. Explicit content (high)

These error messages indicate that the AI has detected content related to restricted topics and has refused to process the request to ensure safety and ethical compliance.


An example of a denied answer

Note: The model will not give you direct instructions, you should rephrase your inquiry!


An example of a rephrased inquiry after a denied answer


Did you like our mini blog series how to fine-tune AI/LLM models?

Please leave a like grinning face with smiling eyes rocket 


Discover the World of AI Optimization: Our New Blog Series is Here! 🚀



Warning: Fine-tuning your own model comes with significant costs depending on the dataset! Always evaluate the potential costs before beginning to fine-tune any model!


Log in to Azure Portal with a University of Vienna ("u:account") account.

Note: Make sure you have an active Microsoft Azure account, associated with your u:account! Visit this ZID page for more info!

Select an Azure AI Foundry project in Azure Portal or make a new one with the "Create a resource" button or use the search field to look for the "Azure AI Foundry" item.

Note: If you log in for the first time or you did not interact with any items before, the "Recent" list will be empty!


After choosing or creating an Azure AI Foundry project, on this screen select "Launch studio".


On this newly-opened webpage you can see the details of the project. In the left side of the screen you can see a menu with different options.

Select "Fine-tuning".


Select "Fine-tune model".

Note: If you did not fine-tune a model before, the list will be empty!


Azure AI Foundry offers several base-models.

You can choose one as a starting point and fine-tune it with custom data.

Select a model from the list.


Here you can see details of the selected model.

Select "Next".


Here you can select "Customize" and change the resource if needed, if not select "Confirm".


Here you can select a version of the model and append a custom suffix.

You also have to choose a resource.

Select "Next".

Note: Version selection is not applicable for all models and appending a suffix is optional!


Here you can specify the location of the fine-tuning data.

Select "Next".


Optional: Here you can select the validation data for the fine-tuning.

Select "Next".


Optional: Here you can customize the fine-tuning parameters if needed, if not select "Next".


Here you can review and modify all the settings and customizations you made once again before beginning with the the fine-tuning.

If you are ready to start the fine-tuning of the model, select "Submit".

Note: This will initiate the fine-tuning process!!!


Reviewing the fine-tuning process


After the fine-tuning process has ended you can see the fine-tuned model listed in the "Fine-tuning" tab.

If you select a newly fine-tuned model in the list you will be able to see all the relevant details about it.


Here you can see all the details related to the fine-tuning and the results.

Select "Metrics" if you want to see more details.


Here you can see a graphical representation of the "train_loss" and "train_mean_token_accuracy" values.

  • train_loss: This metric represents the loss value calculated on the training dataset. It indicates how well the model is performing during training. A lower loss value generally signifies a better fit of the model to the training data.
  • train_mean_token_accuracy: This metric measures the average accuracy of the model in predicting individual tokens (e.g., words or characters) correctly during training. Higher accuracy indicates that the model is making more correct predictions.

Select "Logs" to see more details.


Here you can see the exact details of the fine-tuning.

This is the beginning of the logs.

You can navigate through the logs with "Prev" and "Next".


After navigating to the latest logs you can see how many tokens have been billed by Azure AI Foundry.


Deployment

Note: Deploying a custom model implies extra hourly costs compared to base models!!!

More info about pricing.


The custom model is now ready for deployment!

Select "Models + endpoints".

Here you can see all the deployed models.

Select "Deploy model".

From the drop-down menu select "Deploy fine-tuned model".


Here you can deploy the freshly fine-tuned model.

Select "Submit".

Note: After deploying the model you can see it added in the "Models + endpoints" tab's list!


The model is now ready to be used!

Select the "Playgrounds" tab.

Select "Try the Chat playground".


Here you can select the fine-tuned model from the "Deployment" drop-down menu.

You can start the chat with the model right away!


What's next?

On 7/14/2025 we'll continue our guide how to use language while communicating with AI/LLM models.



Discover the World of AI Optimization: Our New Blog Series is Here! 🚀



To fine-tune large language models (LLMs) in Azure AI Foundry, you need to prepare your data in a specific format, called the "conversation format".


JSON Lines (JSONL) is a format where each line is a valid JSON object. This format is efficient for processing large datasets since each line is a separate JSON object, making it easy to read and write incrementally.

The conversation format is designed to represent dialogues or interactions. Each JSON object should contain the following fields:

  • messages: An array of message objects.
  • role: The role of the speaker (e.g., "user" or "assistant").
  • content: The text content of the message.

An example of a JSONL formatted dataset:

JSONL example
{"messages": [{"role": "user", "content": "Hello, how are you?"}, {"role": "assistant", "content": "I'm good, thank you! How can I assist you today?"}]}
{"messages": [{"role": "user", "content": "What's the weather like today?"}, {"role": "assistant", "content": "The weather is sunny with a high of 75°C."}]}


An example of a JSONL formatted dataset, scarped from several "Studieren" websites of the University of Vienna:

JSONL data from "Studieren"
{"messages": [{"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "user", "content": "Studieren an der Universität Wien"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": "Zulassung"}, {"role": "user", "content": "Aufnahme-/ Eignungsverfahren"}, {"role": "user", "content": "Studienbeitrag"}, {"role": "user", "content": "Studienorganisation"}, {"role": "user", "content": "Absolvent*innen"}, {"role": "user", "content": "Barrierefrei studieren"}, {"role": "user", "content": "Wiederaufnahme"}, {"role": "user", "content": "Web-Services"}, {"role": "user", "content": " Aktuelles aus Studium und Lehre"}, {"role": "user", "content": "Beginn der Antragsfrist für Bachelor-, Diplom und Masterstudien"}, {"role": "user", "content": "First Generation - Workshops im November und Dezember!"}, {"role": "user", "content": "Let's Talk"}, {"role": "user", "content": "Ausschreibung PRO SCIENTIA Stipendien 2025/26"}, {"role": "user", "content": "CAREseiten zeigen - Programm 2024"}, {"role": "user", "content": "Digitale Studienwahl: virtuelle Reise durchs Bachelorstudium "}, {"role": "user", "content": " Unsere nächsten Veranstaltungen"}, {"role": "user", "content": "Online-Infovortrag Studienberechtigungsprüfung"}, {"role": "user", "content": "Online-Infovortrag – Zulassung zu Bachelorstudien (Nicht-EU/EWR)"}, {"role": "user", "content": "Online-Infovortrag – Zulassung zu Masterstudien"}, {"role": "user", "content": "Externe Serviceangebote & Kooperationen"}, {"role": "user", "content": " Sie haben noch Fragen?"}, {"role": "user", "content": " Die Universität Wien auf einen Blick"}, {"role": "user", "content": " Kontakt"}, {"role": "user", "content": " Web-Services"}, {"role": "user", "content": " TIPP zu externen Services"}, {"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "assistant", "content": "Aufgrund der vielen Anträge auf Zulassung zum Studium dauert die Bearbeitung momentan länger. Anfragen zum Stand der Bearbeitung werden nicht bearbeitet. Wir bitten um Ihr Verständnis und danken für Ihre Kooperation."}, {"role": "assistant", "content": "Aufgrund der vielen Anträge auf Zulassung zum Studium dauert die Bearbeitung momentan länger. Anfragen zum Stand der Bearbeitung werden nicht bearbeitet. Wir bitten um Ihr Verständnis und danken für Ihre Kooperation."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "Die Antragsfrist für Studien ohne Aufnahme-/Eignungsverfahren hat am 11. November begonnen!"}, {"role": "assistant", "content": "Du überlegst als 1. in deiner Familie zu studieren? In den First-Generation-Workshops findest du Unterstützung!"}, {"role": "assistant", "content": "Noch Fragen zur Zulassung? Dann können Sie bei der Vor-Ort-Information Let’s Talk persönlich Ihre Fragen stellen. "}, {"role": "assistant", "content": "Die Studienstiftung PRO SCIENTIA bietet hochbegabten Studierenden aller Fachrichtungen Raum für interdisziplinäre Diskussion und Vernetzung."}, {"role": "assistant", "content": "Die Vorträge richten sich an Mitarbeitende und Studierende aller Netzwerk- Universitäten in Österreich. Die Reihe greift Care-Themen auf und fragt..."}, {"role": "assistant", "content": "Digitale Unterstützung für Studienwahl und Aufnahmetests."}, {"role": "assistant", "content": "Sie haben keine Reifeprüfung, wollen aber ein Bachelor- oder Diplomstudium beginnen? "}, {"role": "assistant", "content": "Sie haben Interesse an einem Bachelor-/Diplomstudium an der Universität Wien? Besuchen Sie unseren Online-Infovortrag am 20. November 2024!"}, {"role": "assistant", "content": "Sie haben Interesse an einem Masterstudium ohne Aufnahmeverfahren? Besuchen Sie unseren Online-Infovortrag am 27. November 2024!"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "Bezahlte Anzeige."}, {"role": "assistant", "content": "Über das Kontaktformular erreichen Sie am schnellsten die zuständigen Ansprechpartner*innen."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "Bezahlte Anzeige."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}]}
{"messages": [{"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "user", "content": "Studienangebot der Universität Wien"}, {"role": "user", "content": "Kennen Sie schon das Studium ...?"}, {"role": "user", "content": "Afrikawissenschaften (BA)"}, {"role": "user", "content": "Europäische Ethnologie (MA)"}, {"role": "user", "content": "Tipps zur Studienwahl"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": "Bachelor- und Diplomstudien"}, {"role": "user", "content": "Masterstudien"}, {"role": "user", "content": "Doktorats-/PhD-Studien"}, {"role": "user", "content": "Lehramtsstudien"}, {"role": "user", "content": "Erweiterungscurricula"}, {"role": "user", "content": "Postgraduale Weiterbildung"}, {"role": "user", "content": "Student Mobility - Austausch- & Mobilitätsprogramme"}, {"role": "user", "content": "Weitere Angebote für Studierende"}, {"role": "user", "content": "Universitätssportinstitut"}, {"role": "user", "content": "Sprachenzentrum"}, {"role": "user", "content": " Sie haben noch Fragen?"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": " Kontakt"}, {"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "assistant", "content": "Die Universität Wien verfügt als eine der traditionsreichsten und größten Universitäten Europas über ein vielfältiges Studienangebot. Dieses reicht von Bildung, Philosophie und Religion, Geschichte, Gesellschaft und Politik über Kunst, Kultur und Medien, Mathematik, Informatik und Technik, Naturwissenschaften, Psychologie, Gesundheit und Sport bis Sprachen, Wirtschafts-, Sozial- und Rechtswissenschaften."}, {"role": "assistant", "content": "Diese Vielfalt bietet Studieninteressierten die Chance, jenen Studienweg zu wählen, der den eigenen Vorstellungen und Neigungen am besten entspricht. "}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Anaïs Angelo"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "Weitere Informationen erhalten Sie beim jeweiligen StudienServiceCenter (SSC) bzw. bei der jeweiligen StudienServiceStelle (SSS)."}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}]}
{"messages": [{"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "user", "content": "Auf der Suche nach einem Studium?"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": "Studienwahl - Schule trifft Uni"}, {"role": "user", "content": "Studieren - Ja oder Nein?"}, {"role": "user", "content": "Mach jetzt den uni:check!"}, {"role": "user", "content": "Rund um den Studienbeginn"}, {"role": "user", "content": "Lernen Sie die Universität Wien kennen!"}, {"role": "user", "content": "Lernen Sie die Universität Wien kennen!"}, {"role": "user", "content": "News & Events"}, {"role": "user", "content": "Beginn der Antragsfrist für Bachelor-, Diplom und Masterstudien"}, {"role": "user", "content": "First Generation - Workshops im November und Dezember!"}, {"role": "user", "content": "Let's Talk"}, {"role": "user", "content": "Ausschreibung PRO SCIENTIA Stipendien 2025/26"}, {"role": "user", "content": "Digitale Studienwahl: virtuelle Reise durchs Bachelorstudium "}, {"role": "user", "content": " Unsere nächsten Veranstaltungen"}, {"role": "user", "content": "Online-Infovortrag Studienberechtigungsprüfung"}, {"role": "user", "content": "Online-Infovortrag – Zulassung zu Bachelorstudien (Nicht-EU/EWR)"}, {"role": "user", "content": "Online-Infovortrag – Zulassung zu Masterstudien"}, {"role": "user", "content": " Sie haben noch Fragen?"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": " Kontakt"}, {"role": "user", "content": "Angebote für Schulklassen"}, {"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "assistant", "content": "Sie interessieren sich für die Universität Wien und sind noch auf der Suche nach einem Studium? Die folgenden Seiten unterstützen dabei, das vielfältige Studienangebot kennenzulernen und geben Tipps, wie die Studienwahl leichter gelingt."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien/ Barbara Mair"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien/ Christoph Wannerer"}, {"role": "assistant", "content": "Die Universität Wien organisiert Messen und ist auf Messen vertreten. Sie wollen die Uni kennen lernen und informieren sich gern durch persönliche Gespräche?"}, {"role": "assistant", "content": "Besuchen Sie uns auf einer Messe!"}, {"role": "assistant", "content": "Die Antragsfrist für Studien ohne Aufnahme-/Eignungsverfahren hat am 11. November begonnen!"}, {"role": "assistant", "content": "Du überlegst als 1. in deiner Familie zu studieren? In den First-Generation-Workshops findest du Unterstützung!"}, {"role": "assistant", "content": "Noch Fragen zur Zulassung? Dann können Sie bei der Vor-Ort-Information Let’s Talk persönlich Ihre Fragen stellen. "}, {"role": "assistant", "content": "Die Studienstiftung PRO SCIENTIA bietet hochbegabten Studierenden aller Fachrichtungen Raum für interdisziplinäre Diskussion und Vernetzung."}, {"role": "assistant", "content": "Digitale Unterstützung für Studienwahl und Aufnahmetests."}, {"role": "assistant", "content": "Sie haben keine Reifeprüfung, wollen aber ein Bachelor- oder Diplomstudium beginnen? "}, {"role": "assistant", "content": "Sie haben Interesse an einem Bachelor-/Diplomstudium an der Universität Wien? Besuchen Sie unseren Online-Infovortrag am 20. November 2024!"}, {"role": "assistant", "content": "Sie haben Interesse an einem Masterstudium ohne Aufnahmeverfahren? Besuchen Sie unseren Online-Infovortrag am 27. November 2024!"}, {"role": "assistant", "content": "Über das Kontaktformular zum Thema \"Schule trifft Uni und Schulvorträge\" erreichen Sie am schnellsten die zuständigen Ansprechpartner*innen."}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}]}
{"messages": [{"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "user", "content": "Warum hier studieren?"}, {"role": "user", "content": "Studierende"}, {"role": "user", "content": "rund 90.000"}, {"role": "user", "content": "Ordentliche Studien"}, {"role": "user", "content": "178"}, {"role": "user", "content": "Erfahrung"}, {"role": "user", "content": "über 650 Jahre"}, {"role": "user", "content": "Wir haben das größte Studienangebot"}, {"role": "user", "content": "Wir sind vielfältig & international"}, {"role": "user", "content": "Bei uns gehen Forschung & Lehre Hand in Hand"}, {"role": "user", "content": "Wir sind im Herzen Wiens"}, {"role": "user", "content": "Uni-Einblicke"}, {"role": "user", "content": " Sie haben noch Fragen?"}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": " Kontakt"}, {"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "assistant", "content": "Die Universität Wien ist mit ihren rund 90.000 Studierenden und einem Angebot von 178 ordentlichen Studien sowie über 60 Universitätslehrgängen die vielfältigste und größte Bildungseinrichtung in Österreich."}, {"role": "assistant", "content": "davon rund ein Drittel nicht-österreichische Student*innen aus insgesamt 140 verschiedenen Ländern"}, {"role": "assistant", "content": "Zahlen, Daten & Publikationen"}, {"role": "assistant", "content": "davon über 110 Masterstudien"}, {"role": "assistant", "content": "Studien von A-Z"}, {"role": "assistant", "content": "die älteste Universität im deutschen Sprachraum & eine der ältesten Universitäten Europas"}, {"role": "assistant", "content": "Geschichte der Universität Wien"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Von A wie Afrikawissenschaften bis Z wie Zoologie: Unsere Studierenden wählen aus dem größten Studienangebot in Österreich. Die Universität Wien bietet 178 ordentliche Studien an, darunter über 110 Masterstudien."}, {"role": "assistant", "content": "Wer an der Universität Wien studiert, ist Teil einer großen, vielfältigen und diversen Community von Studierenden aus 140 verschiedenen Ländern. Durch unsere Beteiligung an Netzwerken wie Erasmus+ und Partnerschaften mit den besten Universitäten der Welt eröffnen sich zahlreiche spannende Austauschmöglichkeiten. Diversität wird an der Universität Wien gepflegt, indem das Prinzip der Chancengleichheit in allen Bereichen der Universität Anwendung findet."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien / derknopfdruecker.com"}, {"role": "assistant", "content": "Mit 7.400 Wissenschafter*innen ist die Universität Wien die größte Forschungs- und Bildungseinrichtung Österreichs. Nach dem Prinzip der forschungsgeleiteten Lehre bringen unsere Lehrenden ihre neuesten Ergebnisse direkt in die Lehrveranstaltung und binden die Studierenden früh in Forschungsprozesse ein. Die Universität Wien setzt dabei zukunftsorientierte Akzente in interdisziplinären, innovativen Forschungsfeldern."}, {"role": "assistant", "content": "Mit über 70 Standorten prägt die Universität Wien das Wiener Stadtbild. Die österreichische Hauptstadt belegt in internationalen Ranglisten der Städte mit der besten Lebensqualität immer wieder Platz 1 und gehört auch zu den beliebtesten Studierendenstädten der Welt."}, {"role": "assistant", "content": ""}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Das Hauptgebäude der Universität Wien beherbergt einige Institute, wie das Institut für Geschichte, sowie zentrale Serviceeinrichtungen, wie die Universitätsbibliothek.\r"}, {"role": "assistant", "content": "© Universität Wien / Alex Schuppich"}, {"role": "assistant", "content": "Den Arkadenhof findet man im Inneren des Hauptgebäudes: Hier kann man bei schönem Wetter lernen oder auch einfach nur die Sonne genießen.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Der größte Hösaal im Hauptgebäude der Universität Wien ist das Audimax, welches im Saal und am Balkon über 750 Sitzplätze bietet.\r"}, {"role": "assistant", "content": "© Universität Wien / Franz Pfluegl"}, {"role": "assistant", "content": "Gut lernen und arbeiten kann man auch in anderen Standorten der Universitätsbibliothek - den Fachbereichsbibliotheken (FB) - wie hier z.B. in der FB für Bildungswissenschaft, Sprachwissenschaft und Vergleichende Literaturwissenschaft in der Sensengasse 3a.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Ein Standort der Universität Wien ganz in der Nähe des Hauptgebäudes ist das NIG - das Neue Institutsgebäude. Hier findet man z.B. das Institut für Kultur- und Sozialanthropologie oder für Philosophie.\r"}, {"role": "assistant", "content": "© Universität Wien / Peter Wienerroither"}, {"role": "assistant", "content": "Ein weiterer Standort der Universität Wien ist der Campus. Hier findet man z.B. das Institut für Kunstgeschichte oder für Romanistik. Mit seinen vielen begrünten Innenhöfen bietet der Campus Raum für Ruhe und Erholung mitten in der Stadt.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Im Campus, genauer in Hof 2, findet man das \"Hörsaalzentrum\" mit den Hörsälen C1 und C2.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Der HS C1 im Hörsaalzentrum (UniCampus) ist modern eingerichtet und fasst bis zu 450 Personen. Wenn er besonders voll ist, freut man sich wieder auf all die frische Luft draußen.\r"}, {"role": "assistant", "content": "© Universität Wien / derknopfdruecker.com"}, {"role": "assistant", "content": "Das Institut für Publizistik- und Kommunikationswissenschaft und die Fakultät für Informatik befinden sich in der Währinger Straße 29. Dieses Gebäude ist erst seit 2012 in Betrieb und bietet großzügigen Lern- und Kommunikationsraum für Studierende.\r"}, {"role": "assistant", "content": "© Universität Wien / Gebhard Sengmueller"}, {"role": "assistant", "content": "Den Innenhof der Währinger Straße 29 können Studierende bei schönem Wetter als Lern- und Kommunikationsraum nutzen.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Für den Standort am Oskar-Morgenstern-Platz 1 hat die Universität Wien den Status als GreenBuilding Partner erhalten. Hier sind die Fakultäten für Mathematik und für Wirtschaftswissenschaften sowie die zugehörigen Bibliotheken untergebracht.\r"}, {"role": "assistant", "content": "© Universität Wien / Gebhard Sengmueller"}, {"role": "assistant", "content": "Ähnlich wie in der Währinger Straße 29 gibt es auch am Oskar-Morgenstern-Platz 1 ausreichend Lern- und Kommunikationszonen für Studierende.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Weiter weg, und zwar im 19. Bezirk, befindet sich der Standort in der Franz-Klein-Gasse 1. Dieser beherbergt z.B. die Institute für Ägyptologie oder Klassische Archäologie. Auf der Rückseite befindet sich das Zentrum für Translationswissenschaft.\r"}, {"role": "assistant", "content": "© Universität Wien / Franz Pfluegl"}, {"role": "assistant", "content": "Am Zentrum für Translationswissenschaft kann man z.B. das Bachelorstudium \"Transkulturelle Kommunikation\" studieren. Den Beruf der*des Simultandolmetscher*in kann man schon mal im Sprachlabor üben.\r"}, {"role": "assistant", "content": "© Universität Wien / Franz Pfluegl"}, {"role": "assistant", "content": "Im 15. Bezirk befindet sich das Zentrum für Sportwissenschaft und Universitätssport. Das Universitätssportinstitut (USI) bietet für Studierende günstige Sportkurse; das Angebot ist vielfältig und reicht von A wie Aquagymnastik bis Z wie Zumba.\r"}, {"role": "assistant", "content": "© Universität Wien / Peter Kubelka"}, {"role": "assistant", "content": "In den meisten Standorten der Universität Wien gibt es Bereiche, wo sich Studierende erholen, sich mit Kolleg*innen austauschen oder lernen können.\r"}, {"role": "assistant", "content": "© Universität Wien / Barbara Mair"}, {"role": "assistant", "content": "Über das Kontaktformular zum Thema \"Schule trifft Uni und Schulvorträge\" erreichen Sie am schnellsten die zuständigen Ansprechpartner*innen."}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}]}
{"messages": [{"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "user", "content": "Statistische Daten"}, {"role": "user", "content": "Statistische Daten zur Universität Wien"}, {"role": "user", "content": "Bestätigungen"}, {"role": "user", "content": ""}, {"role": "user", "content": "Studienangebot"}, {"role": "user", "content": " Kontakt"}, {"role": "user", "content": "Informationen für ..."}, {"role": "user", "content": "Meistgesuchte Services ..."}, {"role": "assistant", "content": "Öffentliche Daten und Statistiken zum Hochschulbereich für Österreich insgesamt und je Universität finden Sie frei zugänglich auf den Seiten des Bundesministeriums für Bildung, Wissenschaft und Forschung und der Statistik Austria:"}, {"role": "assistant", "content": "Sie finden hier, nach Semestern aufgelistet, Details zu den Studierendenzahlen der Universität Wien."}, {"role": "assistant", "content": "Bitte beachten Sie, dass in der Summenzeile zu Beginn jedes Berichts auch mitbelegende Studierende inkludiert sind - diese sind mit ihren Studien jeweils auf den letzten Seiten ausgewiesen. Die Abschlüsse beziehen sich jeweils auf den Zeitraum 1. Dezember bis 30. April für das jeweilige Wintersemester und 1. März bis 30. November für das Sommersemester. Die Daten für das aktuelle Semester werden in der Regel wöchentlich aktualisiert."}, {"role": "assistant", "content": "Sind die Auswertungen und Statistiken für Ihre Anliegen nicht ausreichend, erstellt die Koordination Studienservices für Sie nach Möglichkeit gerne Auswertungen zu individuellen Fragestellungen. Bitte setzen Sie sich mit uns per E-Mail an statistik.slw(at)univie.ac.at in Verbindung, damit die Datenverfügbarkeit, die Datenqualität und die Machbarkeit geklärt werden können."}, {"role": "assistant", "content": "Informationen zu Bestätigungen für"}, {"role": "assistant", "content": "sowie zum Erhalt von Bestätigungen finden Sie hier."}, {"role": "assistant", "content": "Derzeit werden unsere Berichte überarbeitet."}, {"role": "assistant", "content": "In der Zwischenzeit besteht die Möglichkeit, statistische Daten über unidata.gv.at abzurufen."}, {"role": "assistant", "content": "Statistik Studierende detailliert 2019W"}, {"role": "assistant", "content": "STUDSTAT 72 2019W.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2019S"}, {"role": "assistant", "content": "STUDSTAT 72 2019S.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2018W"}, {"role": "assistant", "content": "studstat 72 2018W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.7 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2018S"}, {"role": "assistant", "content": "studstat 72 2018S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2017W"}, {"role": "assistant", "content": "studstat 72 2017W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2017S"}, {"role": "assistant", "content": "studstat 72 2017S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.7 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2016W"}, {"role": "assistant", "content": "studstat 72 2016W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.8 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2016S"}, {"role": "assistant", "content": "studstat 72 2016S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.7 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2015W"}, {"role": "assistant", "content": "studstat 72 2015W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.7 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2015S"}, {"role": "assistant", "content": "studstat 72 2015S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2014W"}, {"role": "assistant", "content": "studstat 72 2014W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.7 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2014S"}, {"role": "assistant", "content": "studstat 72 2014S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2013W"}, {"role": "assistant", "content": "studstat 72 2013W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2013S"}, {"role": "assistant", "content": "studstat 72 2013S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2012W"}, {"role": "assistant", "content": "studstat 72 2012W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2012S"}, {"role": "assistant", "content": "studstat 72 2012S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2011W"}, {"role": "assistant", "content": "studstat 72 2011W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2011S"}, {"role": "assistant", "content": "studstat 72 2011S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2010W"}, {"role": "assistant", "content": "studstat 72 2010W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2010S"}, {"role": "assistant", "content": "studstat 72 2010S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2009W"}, {"role": "assistant", "content": "studstat 72 2009W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.5 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2009S"}, {"role": "assistant", "content": "studstat 72 2009S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2008W"}, {"role": "assistant", "content": "studstat 72 2008W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 1.6 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2008S"}, {"role": "assistant", "content": "studstat 72 2008S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.1 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2007W"}, {"role": "assistant", "content": "studstat 72 2007W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.2 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2007S"}, {"role": "assistant", "content": "studstat 72 2007S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.1 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2006W"}, {"role": "assistant", "content": "studstat 72 2006W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.2 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2006S"}, {"role": "assistant", "content": "studstat 72 2006S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.1 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2005W"}, {"role": "assistant", "content": "studstat 72 2005W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.2 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 2005S"}, {"role": "assistant", "content": "studstat 72 2005S akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.3 MB"}, {"role": "assistant", "content": "Statistik Studierende detailliert 200W"}, {"role": "assistant", "content": "studstat 72 2004W akt.pdf"}, {"role": "assistant", "content": "Dateigröße: 2.4 MB"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}, {"role": "assistant", "content": "Sitemap | Impressum | Barrierefreiheit | Datenschutz­erklärung | Druckversion"}]}


Errors

Note: Ensure that your JSONL file is correctly formatted. Each line should be a valid JSON object, and there should be no trailing commas or syntax errors!

  1. If your dataset contains an empty line beginning with "{"messages": []}" is considered a bad syntax and Azure AI Foundry won't let it pass until you remove the empty lines!
  2. If your dataset is not correctly formatted Azure AI Foundry might falsely flag your dataset harmful with the following errors:


    1. Status : Training file: Preprocessing Summary:

    2. Samples of harmful lines per harm type: "THE FOUND HARM TYPE"


Note: If you encounter any of these errors, the Azure AI Foundry will also list on which lines they did occur, so you can easily correct your dataset with a plain text editor or IDE!


Preparing the dataset

A correctly formatted dataset is essential for fine-tuning.

You can visit the ZID's Phaidra-GitLab page and find the gitlab project of Coordination Digital Transformation where there are two scripts available that can scrape any public website.

One script is used to extract JSON data from websites.

The other is used to extract data in JSONL format.


Note: The scripts double check the UFT-8 formatting of the data with German (DE) character support, preventing the above mentioned second error, which usually occurs due to bad character formatting and not because of actually finding harmful content!


What's next?

On 7/7/2025 we'll continue our guide how to fine-tune AI/LLM models.

Entdecken Sie die Welt der KI-Optimierung: Unsere neue Blogreihe startet! 🚀
In den kommenden Wochen tauchen wir tief in die spannende Welt der KI und Large Language Models (LLMs) ein. Freuen Sie sich auf praxisnahe Einblicke und wertvolle Tipps! – alle Beiträge werden auf Englisch sein.

1️⃣ Daten richtig vorbereiten – So legst du die perfekte Grundlage für erfolgreiches Fine-Tuning.
InhaltUm KI-Sprachmodelle in Azure AI Foundry schlauer zu machen, müssen Sie Ihre Daten in einem speziellen Format, dem sogenannten „Konversationsformat“, organisieren. Dafür wird ein einfacher Dateityp namens JSON Lines verwendet, bei dem jede Zeile eine Information enthält – wie ein Satz in einer Geschichte. Das ist ideal, um große Datenmengen einfach zu verarbeiten. Unser Leitfaden zeigt Ihnen Schritt für Schritt, wie Sie Ihre Daten vorbereiten. Machen Sie Ihre KI bereit, mit Ihren eigenen Ressourcen zu lernen!
Veröffentlichung: am 30.06.25


2️⃣ Optimierung in Azure AI Foundry – Entfessle das volle Potenzial deiner Modelle.
Inhalt: Dieses Tutorial hilft Ihnen, KI-Sprachmodelle in Azure AI Foundry neue Fähigkeiten beizubringen. Es ist wie ein Handbuch mit klaren Anleitungen und vielen Bildern. Folgen Sie einfach den Schritten, um Ihr KI-Modell anzupassen. Tauchen Sie ein und machen Sie Ihre KI mit Ihren eigenen Daten schlauer!
Veröffentlichung: am 07.07.25


3️⃣ Die richtige Sprache finden – Wie du mit LLMs effektiv kommunizierst.
Inhalt: Mit KI-Sprachmodellen zu sprechen ist, als würde man mit einem superschlauen Freund chatten – man muss klar formulieren, um tolle Antworten zu bekommen. Dieser Leitfaden gibt einfache Tipps, wie Sie Fragen stellen oder Anweisungen geben, um die besten Ergebnisse zu erzielen. Lernen Sie unkomplizierte Wege, damit Ihre KI Sie besser versteht. Perfekt für alle, die mehr aus ihren KI-Gesprächen herausholen möchten. Starten Sie wie ein Profi mit unseren hilfreichen Ratschlägen!
Veröffentlichung: am 14.07.25

Bleiben Sie dran und lassen Sie sich inspirieren – jede Woche ein neuer Beitrag! 💡


--------------------------- * english version * ---------------------------


Discover the World of AI Optimization: Our new blog series is here! 🚀
In the coming weeks, we’ll dive deep into the exciting world of AI and Large Language Models (LLMs). Get ready for practical insights and valuable tips!

1️⃣ Preparing Your Data – Learn how to lay the perfect foundation for successful fine-tuning.
Content: To make AI language models smarter in Azure AI Foundry, you need to organize your data in a special way called the "conversation format." This uses a simple file type called JSON Lines, where each line holds a piece of information, like a sentence in a story. It’s great for handling lots of data easily. This guide shows you how to set up your data step-by-step. Get your AI ready to learn your own resources!
Release: 06/30/2025


2️⃣ Optimizing in Azure AI Foundry – Unlock the full potential of your models.
Content: This tutorial helps you teach AI language models new tricks in Azure AI Foundry. It’s like a guidebook, with clear steps and lots of pictures. Just follow along to customize your AI model. Dive in and make your AI smarter with your own data!
Release: 07/07/2025


3️⃣ Choosing the Right Language – How to communicate effectively with LLMs.
Content: Talking to AI language models is like chatting with a super-smart friend—you need to be clear to get great answers. This guide shares easy tips on how to ask questions or give instructions for the best results. Learn simple ways to make your AI understand you better. It’s perfect for anyone wanting to get more out of their AI conversations. Start communicating like a pro with our helpful advice!
Release: 07/14/2025

Stay tuned and get inspired – a new post every week! 💡


 




Die Projekte aus der Ausschreibung zur "Digitalen und Sozialen Transformation in der Hochschulbildung" wurden im Zeitraum 2020 bis 2024 umgesetzt und sind nun abgeschlossen. Die Stabsstelle "Koordination Digitale Transformation" des ZID sorgte für die übergreifende Projektkoordination seitens Universität Wien, unterstützt vom Büro des Rektorats, der DLE FinCo sowie der DLE Komm. Im Zuge des Projektabschlusses fanden entsprechende Veranstaltungen statt, die u.a. über Projektwebseiten, u:wiki und andere Kanale kommuniziert und beworben wurden.

check mark button  Mit Ende April 2025 sind die Abschlussberichte und Management Summaries an das BMFWF übermittelt worden. Letztere sollen durch das BMFWF veröffentlicht werden. 

Gesamtüberblick:

  • Die Projekte sind im Großen und Ganzen nach Plan verlaufen. Abgesehen von geringfügigen Verschiebungen und Anpassungen, größtenteils durch die Corona-Pandemie bedingt, sind keine signifikanten Abweichungen von den Meilensteinen zu berichten. Details sind den Anhängen zu entnehmen.
  • Mit Hilfe der Finanzierung des BMFWF konnten eine Vielzahl an Projektmitarbeiter*innen eingestellt und Services auf- bzw. ausgebaut werden. Diverse Services wurden, wo sinnvoll, auch personell verstetigt.
  • Der öffentliche Informations- und Kollaborationsbereich ist hier im u:wiki zu finden. Er dient auch nach Auslaufen der Projekte als Archiv und Informationshub.

Management Summaries der von der Universität Wien geleiteten Projekte

Highlights der verstetigten Ergebnisse 

Projekte unter Leitung der Universität Wien

  • Austrian Transition to Open Access 2 (AT2OA2)
    • Open Access (OA) – Freier Zugang zu wissenschaftlichem Wissen
      • Erweiterung der Möglichkeiten für Open Access-Publikationen, u.a. durch neue ("transformative") Verlagsabkommen
      • Erheben und Analysieren von Publikationskosten – Austrian Datahub for Open Access Negotiations and Monitoring
      • Auseinandersetzung mit dem Phänomen Predatory Publishing (dem „räuberischen Publizieren“ i.S.v. hohen Kosten bei geringer Qualitätssicherung)

      • Auswirkungen auf die Sichtbarkeit von wissenschaftlichen Publikationen

    • Beteiligung aller öffentlichen Universitäten

  • Digitize! Computational Social Sciences in der digitalen und sozialen Transformation
    • Erfolgreiches Pilotprojekt: Aufbau eines Online-Befragungspanels mit über 4.800 Teilnehmer*innen

    • MOOC "Computational Social Science" unter Mitarbeit aller Projektpartner*innen aus den Sozialwissenschaften, Data Sciences und Rechtswissenschaft

    • Entwicklung Public Value Assessment Tool (PLUTO), online verfügbar: https://pluto.univie.ac.at/ 

    • Entwicklung eines österreichbezogenen Word-Embedding Modell, online verfügbar: https://meteor.opted.eu/

  • Open Education Austria Advanced (OEAA)
  • Teaching Digital Thinking (TDT)
    • Neuer Masterstudiengang „Computational Social Systems (CSSs)“ an TU Graz & Uni Graz
    • Lehrkooperation „Route 63” von TU Graz & Uni Graz
    • MOOC-Serie „Digitales Leben"
    • Wahlpaket „Digital Science“ an der Universität Innsbruck
    • Erweiterungsstudium Informatik an der Universität Innsbruck
    • edukatives Softwaresystem Selfie an der Universität Salzburg (Informatik theoretisch und praktisch erlernen)

Projekte mit Beteiligung der Universität Wien

  • AHESN Next (Lead: Uni Klagenfurt)
    • Einheitliche Schnittstellen für Campus Management Systeme zum Austausch von bspw. Anerkennungen
  • Digital Blueprint (Lead: TU Graz)
    • ID Austria Anbindung bspw. im Studienzulassungsprozess
  • Digital University Hub (Lead: TU Graz)
    • Universitätsübergreifende projektbezogene Austauschplattform
  • Digital University Toolkit (Lead: TU Graz)
    • Leichtere Installation von externen Phaidra-Instanzen
  • iMooX (Lead: TU Graz)
    • Österreichweite MOOC Plattform, bei der alle MOOCs der Uni Wien abgerufen werden können
  • RIS Synergy (Lead: TU Wien)
    • Automatischer Datenaustausch mit Forschungsförderern


Open Educational Resources - OER

https://oer.univie.ac.at/

University of Vienna staff can now complete the "OER-Practitioner" training free of charge and become certified experts in Open Educational Practices (1 ECTS, including workshop on-site, asynchronous MOOC participation, publication of 3 OER). Upon completion, participants receive the official OER certificate. Currently there are 224 certified OER-Practitioners in the Austrian Higher Education Sector and 26 certifications for Higher Education Institutions.


This training supports the University’s OER policy, adopted in summer 2024, and strengthens our path toward becoming an OER-certified higher education institution. University of Vienna has already fulfilled the first two key criteria:

  • A public commitment to OER and a dedicated training offer (OER policy)
  • Access to an OER repository (PHAIDRA, connected to the OERhub)


More on the Austrian OER certification is organised by fnma (Forum Neue Medien in der Lehre Austria) here:
OER Certification for Higher Education Institutions


More information on the OER-Practitioner-Training @ University of Vienna here:

https://oer.univie.ac.at/weiterbildungsangebote-fuer-universitaetsangehoerige/


I would like to invite you or/and your interested colleagues to join one of our training-workshops - the dates for this semester are:


Training for all University staff: Teaching Competence Workshop

  • Date: 13 May 2025, 9:00–13:00
  • Location: CTL, Universitätsstraße 5
  • Title: " Synergien von Open Science and Open Education nutzen"
  • Register: via u:rise
    ⚠️ Registration via u:rise is closed — I can arrange late registration if needed.

 

Training for Student Research / Teaching Assistants at University: QuaM! Workshop (Qualifizierung für studentische Multiplikator*innen)

  • Date: 14 May 2025, 9:00–13:00
  • Location: Augasse 2–6, SR 5.48 (5th floor)
  • Title: "Working with Open Educational Resources (OER) at the University of Vienna"
  • Register: via Moodle

Save the Date!

Im Rahmen des Horizon Europe Projekts Skills4EOSC veranstalten das Naturhistorischen Museum Wien in Zusammenarbeit mit dem EOSC Support Office Austria einen Austausch zum Thema Open Science in der EU und Österreich. Die Veranstaltung richtet sich an Personen aus Politik, Verwaltung, Wissenschaft und Wissenschaftsvermittlung, um Entwicklungen und Strategien von Open Science in Österreich zu diskutieren. Ziel der Veranstaltung ist, die Open Science Community in Österreich zu unterstützen. Dafür werden zentrale Ergebnisse aus dem Skills4EOSC Projekt vorgestellt, in dem speziell für Entscheidungsträger*innen Trainingsmaterialien zum Thema Open Science entwickelt wurden. 


Datum: 08. April 2025 von 15:00 bis 16:30 Uhr

Webinar ”Die Bedeutung von wissenschaftlichen Sammlungen und Open Science Kompetenzen für Politik, Kultur, Wissenschaft und Kunst in Österreich”


Nähere Details zu der Veranstaltung finden Sie im Flyer.

Um Anmeldung über folgenden Link wird gebeten: https://ec.europa.eu/eusurvey/runner/NationalPilotTraining-EvidenceBasedPolicy-AT


Save the Date!

Der Cluster Forschungsdaten lädt herzlich zur Expo am Donnerstag, dem 16. Jänner 2025 an die TU Wien. Der thematische Schwerpunkt wird auf Forschungsinformationssysteme, Forschungsdatenmanagement und forschungsunterstützende Infrastrukturen gelegt.

Datum: 16. Januar 2025, TU Wien

Ort: Kuppelsaal, Karlsplatz 13, 1040 Wien, 4. Stock

Zur Anmeldung

Das Programm beinhaltet eine Bandbreite an Vorträgen, Produktdemonstrationen, Posterpräsentationen und Workshops, um die unterschiedlichen und breitgefächerten Infrastrukturen, Tools und Services aus Österreich vorzustellen. Die Veranstaltung schließt mit einer interdisziplinär besetzten Podiumsdiskussion und einem Vernetzungsprogramm am Abend. Am Folgetag besteht die Möglichkeit für Arbeitsgruppentreffen.

Mehr Details finden Sie auf der Homepage des Cluster Forschungsdaten.

 

Mark your calendar for September 23, 2025!

Exposome Austria invites to its “Symposium & Open Stakeholder Day” bringing together researchers, medical experts, and policy makers dedicated in their work to the intersection of human health, environment and chemistry.
Be part of this dialogue driving the global shift from traditional "repair medicine” to more proactive, personalized and preventive healthcare. Do not miss this transformative event. Learn what services the Exposome/EIRENE Austria ESFRI Research Infrastructure can offer.

Have your say in what will be needed in the future!


 

Here you find the flyer with more informations about the event.

Secure your spot at this event by registering via email aexposome.austria@univie.ac.at !


You can also visit the homepage of Exposome Austria.

 

Within the national project "Austrian Transition to Open Access 2 (AT2OA2)" our Subproject 5 - "Visibility of Open Access Publications" was dedicated, among other things, to whether Open Access, in addition to improving the availability of scholarly publications, also contributes to increasing visibility.
Alternative metrics (altmetrics) served as the primary hook and vehicle for investigating this and other questions, since citation-based metrics are no longer the sole indicators of the reception of scientific achievements.
A particular focus of the activities was realizing a study in cooperation with Altmetric (Digital Science).

You will find the complete science comic on Zenodo.

A set of recommendations for researchers on how to increase the visibility of scholarly achievements was formulated as a deliverable.
However, to be honest, how many recommendations are already out there? And how many of them really attract the attention of researchers in its typical presentation? 🤔
The answers are "too many" and "none". That is why we wanted to do a visual translation of these recommendations into a Science Comic that is equally appealing and edutaining.
So enjoy the final product "Standing out of the crowd", which was brilliantly illustrated by none other than the internationally renowned Matteo Farinella.

Farinella, M., Ferus, A., Gumpenberger, C., Hölbling, L., & Schilhan, L. (2024). Standing out of the crowd – How can researchers be more visible?. Zenodo. https://doi.org/10.5281/zenodo.13983337

 

Vizerektor Ronald Maier präsentierte die Aktivitäten zur digitalen Barrierefreiheit an der Universität Wien

Im Rahmen einer Veranstaltung zum vierjährigen Bestehen der Web Accessibility Directive (WAD) der EU wurde die Universität Wien als eines von drei Best Practice Beispielen präsentiert. Vizerektor Maier stellte in seinem Statement die vielfältigen Aktivitäten der Universität vor und betonte, dass Barrierefreiheit nicht nur eine Verpflichtung, sondern auch ein wesentlicher Aspekt der digitalen Kultur an der Universität sei.  

Bei der Veranstaltung wurde auf die ersten vier Jahre der Richtlinie und deren Umsetzung in den Mitgliedsländern zurückgeblickt und ein Ausblick in die Zukunft diskutiert. Veranstalter waren IAAP EU und das European Disability Forum (EDF). Das Web-Zugänglichkeitsgesetz (WZG) ist die österreichische Umsetzung der Web Accessibility Directive.


Der Vortrag von Vizerektor Maier ist in Session 1 zu finden, der direkte Link zum Vortrag lautet: youtube.com/watch?v=B-B2ZBYyIJg#t=17m26s
Die Aufzeichnung der gesamten Veranstaltung finden Sie unter: https://www.youtube.com/playlist?list=PL8nIY-v0zG736NYDI33EwHVdNFrX8O5Y4
(Die Videos stehen leider nur mit schlechter Videoqualität zur Verfügung.)

 

Der neue MOOC „CALLISTO: The basics of corpora and NLP for low-resource languages“ ist ab 30. September verfügbar!

Dieser kurze Einführungskurs bietet einen Einblick darin, wie Sprachenkorpora die Weiterentwicklung von Forschung und Gesellschaft unterstützen und wie sie zum digitalen Überleben von Sprachen mit eingeschränktem Korpus beitragen.

Link zum Online-Kurs: https://imoox.at/course/callisto

MOOC steht für "Massive Open Online Courses". Dahinter steht das iMooX Projekt. Dieses bietet kostenlose Online-Kurse für alle interessierten Personen an. Informieren Sie sich unter https://imoox.at/mooc/


Der neue MOOC „Digitales Leben 5“ ist ab 7. Oktober verfügbar!

In 5 Lektionen diskutieren 5 Expert:innen aus technischer, philosophischer, künstlerischer und aktivistischer Perspektive die Voraussetzungen und Auswirkungen des digitalen Wandels.
Das Kursbild des MOOC „Digitales Leben 5“ wurde vom CTL Universität Wien erstellt.

Link zum Online-Kurs: https://imoox.at/course/digi5

MOOC steht für "Massive Open Online Courses". Dahinter steht das iMooX Projekt. Dieses bietet kostenlose Online-Kurse für alle interessierten Personen an. Informieren Sie sich unter https://imoox.at/mooc/


AURELEO:
Austrian users at LEONARDO supercomputer

In August 2023 the Italian pre-exascale HPC system LEONARDO began the regular operation of its so-called “Booster” module which draws its enormous computing power from four NVIDIA Ampere GPUs per node. Currently (June 2024) it is the seventh most powerful supercomputer in the world and third most powerful in Europe.


Austria has its share of LEONARDO since it is a partner in the consortium that has built the machine and Austrian users are encouraged to take this opportunity to apply for compute time at LEONARDO’s GPU-accelerated “Booster” module. In terms of computational power this share is comparable to the already available GPU partition at the current VSC-5 installation.


Hereby VSC announces this Call for Proposals that could benefit from Booster’s multi-GPU nodes.

Eligibility and responsibilities

  • This call is intended for medium-sized projects (from 50,000 to 100,000 GPU hours) with a duration of 6 or 12 months from resource allocation date.
  • Since the “Booster” module comprises multi-GPU nodes your application must efficiently use at least all 4 GPUs available on the node; this includes embarrassingly parallel implementations.
  • Since VSC has no direct control over time allocation, granted projects need to make sure to use all the resources that have been granted to them, otherwise they are simply lost for Austrian users.

Deadlines

  • Unlike the usual applications for VSC projects, which are submitted in a rolling fashion, and similar to the way it is handled with PRACE or EuroHPC this Call will include cut-offs:
  • The next application cut-off date is 2024-07-07.
  • Notification of acceptance will be sent by 2024-07-26.
  • The projects will start in the beginning of August 2024.

Review of the projects

  • The technical review is performed by VSC staff according to LEONARDO’s guidelines.
  • No additional scientific review is required if the planned computations are carried out within a project that has already been approved by a recognised funding agency, such as FWF, FFG, ÖAW, WWTF, ERC, EU, etc.

High-Level support team is available

  • Every AURELEO project will have one high-level support team member assigned for assistance.
  • For this type of call a user can request additional assistance of specialist support.

Application for projects

  • Note, in order to use LEONARDO every user will have to upload a proof of identity to the UserDB of CINECA (LEONARDO’s hosting entity).
  • For any questions related to this Call, access and usage of LEONARDO, please, write to: leonardo@vsc.ac.at



See also:
https://vsc.ac.at/access/aureleo-austrian-users-at-leonardo-supercomputer

Microsoft Azure

Mitarbeiter*innen, die im Sommersemester 2024 Forschungsaktivitäten in Azure durchführen, können bis 31.12.2023 eine Förderung beantragen.