News
| Aug 21, 2026 | Our paper Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors was accepted to Findings of EMNLP 2026. |
|---|---|
| Jul 14, 2026 | Our recent paper Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors and the TrapQA benchmark homepage are now available online. |
| Apr 10, 2026 | Our paper Understanding and Preserving Safety in Fine-Tuned LLMs was accepted to ACM CCS 2026. |