Scholar
Peter Hase
Google Scholar ID: FO90FgMAAAAJ
Visiting Scientist, Schmidt Sciences
Citations & Impact
Citations
3,333
H-index
20
i10-index
23
Publications
20
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- 2025: Papers accepted at ICLR (on system 1.x reasoning) and NAACL (on persuasion-balanced training).
- 2024: Two papers accepted to TMLR on fundamental problems in model editing and unlearning for multimodal models; one was an Outstanding Paper Finalist.
- 2024: NeurIPS paper on calibrating LLMs’ linguistic expressions of confidence.
- 2024: ICLR spotlight paper on deleting sensitive information from LLMs to defend against extraction attacks.
- 2023: Three NeurIPS papers on localization/model editing, mechanistic interpretability for vision models, and LMs teaching weaker agents.
- 2023: Named Outstanding Area Chair at ACL 2023 (top 1–1.5%).
- 2024: Serving as Senior Area Chair for ACL 2025; was Area Chair for EACL 2024 in Interpretability track.
- Invited talks at Stanford, OpenAI, CHAI (UC Berkeley), TTIC, and others.
