What values drive LLMs? Can they navigate through mazes more easily in English than in Icelandic? How can we measure hallucinations? This TrustLLM webinar will be about evaluating LLMs across languages.

This three-part TrustLLM webinar that took place February 24, 2026.

Annika Simonsen (University of Iceland) presented one of three topics in this webinar: ValEU, a European values benchmark for assessing how closely LLMs align with shared cultural values. ValEU offers a transparent way to probe the moral and societal assumptions embedded in LLMs across countries, topics, and demographic groups. 

Hafsteinn Einarsson (University of Iceland) presented the second topic of this TrustLLM webinar: benchmarking model performance on math problems and maze navigation. 

Freja Thoresen (Alexandra Institute, Copenhagen) presented the third topic of this TrustLLM webinar: hallucinations. They come in two main types: faithfulness and factuality. Freja discussed strategies for detecting hallucinations, including metrics like token‑level classifiers and multilingual benchmark suites.

This webinar was hosted by Jens van der Weide (TNO). 

How do LLMs actually learn new languages? How can LLMs learn small languages like Faroese better? Can LLMs learn languages from images rather than text?

In this three-part TrustLLM webinar that took place February 5, 2026, we look at one of the most overlooked parts of LLM training: tokenization. What is often treated as a preprocessing step shapes how a model learns and how it handles languages with very different amounts of training data.

Garðar Ingvarsson Juto (Miðeind), Ilker Kesen (University of Copenhagen), Andreas Holm (Alexandra Institute) discuss these topics during this webinar, hosted by Jens van der Weide (TNO).

• A half-day seminar exploring how ethics and trust can be built into large language models.
• 20 May 2025, Linköping University, Sweden

Fredrik Heintz, project coordinator at TrustLLM and Professor of Computer Science, Linköping University

Danila Petrelli, Senior Data Manager, AI Sweden

Laurynas Adomaitis, AI Ethics and Governance Researcher at Research institutes of Sweden, RISE Department of Computer Science.