News
| Jan 2026 | Work on Memories in ChatGPT, jointly led by Abhishek, Soumi, Qinyuan and Elisabeth got accepted at WWW'26. |
|---|---|
| Jan 2026 | Debtanu's summer internship work hallucination detection in low resource languages got accepted at EACL'26. |
| Jan 2026 | Qinyuan's paper on work Generalizing over Memorized Data in LLMs got accepted at ICLR'26. |
| Jan 2026 | Leon joined the team as a PhD student. Welcome Leon! |
| Dec 2025 | Our team co-organized the workshop on Metacognition in Generative AI (co-located with EurIPS) with Marcel Binz, Hamed Hassani, Nastaran Okati and Isabel Valera. |
| Nov 2025 | Elisabeth's work on generative search was covered by ArsTechnica, Tagesschau, and Heise. Read the paper here. |
| Nov 2025 | Bilal visited the Social Foundations of Computing group at MPI-IS and spoke about "On Counterfactual Reasoning Abilities of LLMs". |
| Oct 2025 | The pre-print for our paper Characterizing Search in the Age of Generative AI (with Elisabeth Kirsten, Jost Grosse Perdekamp, Mihir Upadhyay and Krishna P. Gummadi) is online. |
| Aug 2025 | Zahra's paper Can LLMs Explain Themselves Counterfactually got accepted at EMNLP'2025. |
| Aug 2025 | Bruno joined the team as a PhD student. Welcome Bruno! |
| Jul 2025 | Bilal gave an invited talk on "On Trustworthiness of LLMs" at the AISA 2025 Symposium. |
| Jun 2025 | Our team co-organized the CASA 2025 Summer School on AI and Security in collaboration with groups of Asja Fischer and Ghassan Karame. |
| Apr 2025 | Elisabeth presented her paper The Impact of Inference Acceleration on Bias of LLMs at NAACL 2025. |
| Mar 2025 | Kick-off of the AI Lecture Series@RUB. |
| Feb 2025 | Bilal gave an invited talk on "On Trustworthiness of LLMs" at the Aleph Alpha. |