#cidas — Public Fediverse posts on home.social

Markus Osterhoff @[email protected] · 2026-01-28 · 08:47 UTC

Ine Gevers (U Antwerp) at #CIDAS Colloquium: Thursday, Feb 5th, 14:15

Playing with Knowledge: Evaluating Common Sense in LLMs Through Language Games

Large Language Models (#LLMs) today achieve strikingly high scores on different benchmarks, designed to test math, language understanding, or coding skills. Yet, these same models can exhibit surprising failures of common sense, like suggesting to use glue on your pizza if the cheese slips off. These mismatches highlight an open question: what do LLMs really understand about the world? Evaluating common sense knowledge in AI systems has been a longstanding challenge in NLP, spanning a wide collection of topics such as implicit language understanding, social or cultural norms, or everyday reasoning strategies.

1/2

#cidas #llms

Markus Osterhoff @[email protected] · 2026-01-28 · 08:47 UTC

Ine Gevers (U Antwerp) at #CIDAS Colloquium: Thursday, Feb 5th, 14:15

Playing with Knowledge: Evaluating Common Sense in LLMs Through Language Games

Large Language Models (#LLMs) today achieve strikingly high scores on different benchmarks, designed to test math, language understanding, or coding skills. Yet, these same models can exhibit surprising failures of common sense, like suggesting to use glue on your pizza if the cheese slips off. These mismatches highlight an open question: what do LLMs really understand about the world? Evaluating common sense knowledge in AI systems has been a longstanding challenge in NLP, spanning a wide collection of topics such as implicit language understanding, social or cultural norms, or everyday reasoning strategies.

1/2

#cidas #llms

Markus Osterhoff @[email protected] · 2026-01-28 · 08:47 UTC

Ine Gevers (U Antwerp) at #CIDAS Colloquium: Thursday, Feb 5th, 14:15

Playing with Knowledge: Evaluating Common Sense in LLMs Through Language Games

Large Language Models (#LLMs) today achieve strikingly high scores on different benchmarks, designed to test math, language understanding, or coding skills. Yet, these same models can exhibit surprising failures of common sense, like suggesting to use glue on your pizza if the cheese slips off. These mismatches highlight an open question: what do LLMs really understand about the world? Evaluating common sense knowledge in AI systems has been a longstanding challenge in NLP, spanning a wide collection of topics such as implicit language understanding, social or cultural norms, or everyday reasoning strategies.

1/2

#cidas #llms

Markus Osterhoff @[email protected] · 2026-01-28 · 08:47 UTC

Ine Gevers (U Antwerp) at #CIDAS Colloquium: Thursday, Feb 5th, 14:15

Playing with Knowledge: Evaluating Common Sense in LLMs Through Language Games

Large Language Models (#LLMs) today achieve strikingly high scores on different benchmarks, designed to test math, language understanding, or coding skills. Yet, these same models can exhibit surprising failures of common sense, like suggesting to use glue on your pizza if the cheese slips off. These mismatches highlight an open question: what do LLMs really understand about the world? Evaluating common sense knowledge in AI systems has been a longstanding challenge in NLP, spanning a wide collection of topics such as implicit language understanding, social or cultural norms, or everyday reasoning strategies.

1/2

#llms #cidas

GWDG @[email protected] · 2025-09-19 · 08:45 UTC

📌 Am Freitag, den 14. November 2025, findet bei der GWDG im Göttinger Rechenzentrum das KI-Event „KI.Connect“ statt – ein Vernetzungs- und Informationsformat für regionale Unternehmen, Wissenschaft, Studierende und Politik.
Auf dem Programm stehen populärwissenschaftliche Vorträge, Workshops und Diskussionen zu aktuellen KI-Anwendungen in Medizin, Agrar, Industrie und Gesellschaft. Ergänzt wird das Event durch einen „Marktplatz“ für Abschlussarbeiten, Networking und Führungen durch das Göttinger Rechenzentrum.