Back to homepage

News archive

2026

  1. I hosted the Birds of a Feather session “Doing NLP Research in Japan” at EMNLP 2026.

  2. I gave a talk on “What Role Can Interpretability Play in AI for Science?” at the symposium “The Future of Science: AI-First, Trustworthy, Human-Steered” at TU Darmstadt.

  3. I gave a talk on “Interpretability Research in the RIKEN AIP NLU Team: Recent Work and Open Questions” at SIG Interpretability at TU Darmstadt’s UKP Lab.

  4. Our new preprint “Do LMs Know What Variables Do? Interpreting Code Representations via Variable Roles” is now available on arXiv.

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

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

  7. Our new preprint “SharedSAE: One Feature Dictionary Across Language Models” is now available on arXiv.

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

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

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