Back to homepage

News archive

2026

  1. I gave a guest lecture on “Analyzing and Interpreting the Internals of Language Models” at the University of Tokyo.

  2. I gave a talk on “Linear Representations in LLM Interpretability: Claims and Evidence” at the TU Darmstadt–RIKEN AIP joint workshop.

  3. Our paper “A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification” has been accepted to EMNLP 2026.

  4. Our new preprint “Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics” is now available on arXiv.

  5. I'll be a tutorial co-chair at ACL 2027.