🧑‍🔬 Peter Henderson

🏛️ Affiliations

🎓Princeton UniversityPrinceton · United States2022–2026 · 43 paperscurrent🎓Stanford UniversityStanford · United States2018–2025 · 29 papersEducation since 2018 · JD-PhD, Computer Science and Law School🎓McGill UniversityMontreal · Canada2011–2019 · 13 papersEducation 2011–2015 · B. Eng., Electrical, Computer, and Software EngineeringEducation 2016–2018 · M.Sc., Computer Science🎓Johns Hopkins UniversityBaltimore · United States2024–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (2023 · 355 citations)
   Current safety alignment methods, such as instruction tuning and RLHF, constrain how a model behaves at inference time.
2. A Reasoning-Focused Legal Retrieval Benchmark (2025 · 55 citations)
   Legal AI tools increasingly pair LLMs with retrievers over case law and statutes, but realistic English benchmarks for testing such pipelines are scarce.

All works

36 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗arXiv:2211.05100 · no summary yetBigScience Workshop et al.2022 · 1,606 citations
2. Holistic Evaluation of Language Models ↗arXiv:2211.09110 · Published in Transactions on Machine Learning Research (TMLR), 2023 · no summary yetPercy Liang et al.2022 · 1,001 citations
3. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!arXiv:2310.03693Xiangyu Qi, Yi Zeng, Tinghao Xie, et al.2023 · 355 citations
4. Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims ↗arXiv:2004.07213 · no summary yetMiles Brundage et al.2020 · 320 citations
5. Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning ↗arXiv (Cornell University) · no summary yetPeter B. Henderson et al.2020 · 258 citations
6. Visual Adversarial Examples Jailbreak Aligned Large Language Models ↗arXiv:2306.13213 · no summary yetXiangyu Qi et al.2023 · 240 citations
7. With Little Power Comes Great Responsibility ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetDallas Card et al.2020 · 173 citations
8. Foundation Models and Fair Use ↗SSRN Electronic Journal · no summary yetPeter B. Henderson et al.2023 · 134 citations
9. When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset ↗arXiv:2104.08671 · no summary yetLucia Zheng et al.2021 · 134 citations
10. Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset ↗arXiv:2207.00220 · no summary yetPeter Henderson et al.2022 · 133 citations
11. Safety Alignment Should Be Made More Than Just a Few Tokens Deep ↗arXiv:2406.05946 · no summary yetXiangyu Qi et al.2024 · 97 citations
12. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ↗arXiv:2406.14598 · no summary yetTinghao Xie et al.2024 · 87 citations
13. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ↗arXiv:2402.05162 · no summary yetBoyi Wei et al.2024 · 66 citations
14. A Reasoning-Focused Legal Retrieval BenchmarkarXiv:2505.03970Lucia Zheng, Neel Guha, Javokhir Arifov, et al.2025 · 55 citations
15. Promises and pitfalls of artificial intelligence for legal applications ↗arXiv:2402.01656 · no summary yetSayash Kapoor, Peter Henderson, Arvind Narayanan2024 · 40 citations
16. Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models ↗Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yetPeter B. Henderson et al.2023 · 36 citations
17. On the Societal Impact of Open Foundation Models ↗arXiv (Cornell University) · no summary yetSayash Kapoor et al.2024 · 30 citations
18. Evaluating Copyright Takedown Methods for Language Models ↗neural information processing systems · no summary yetBoyi Wei et al.2024 · 25 citations
19. A Safe Harbor for AI Evaluation and Red Teaming ↗arXiv (Cornell University) · no summary yetShayne Longpre et al.2024 · 22 citations
20. LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain ↗Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yetJoel Niklaus et al.2025 · 12 citations
21. Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation ↗arXiv:2510.11977 · no summary yetSayash Kapoor et al.2025 · 11 citations
22. The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources ↗arXiv (Cornell University) · no summary yetShayne Longpre et al.2024 · 11 citations
23. Fantastic Copyrighted Beasts and How (Not) to Generate Them ↗arXiv (Cornell University) · no summary yetLuxi He et al.2024 · 9 citations
24. Position: On the Societal Impact of Open Foundation Models ↗ANU Open Research (Australian National University) · no summary yetSayash Kapoor et al.2024 · 6 citations
25. Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs ↗arXiv (Cornell University) · no summary yetDeepak Narayanan et al.2023 · 6 citations

See all 36 works by Peter Henderson →

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Christopher D. Manning
• Daniel E. Ho
• Pin-Yu Chen
• Ruoxi Jia
• Yi Zeng

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• neural information processing systems ×3
• Proceedings of the AAAI/ACM Conference on AI Ethics and Society ×2
• ANU Open Research (Australian National University)
• Findings of the Association for Computational Linguistics: NAACL 2025
• Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
• Proceedings of the National Academy of Sciences
• SSRN Electronic Journal

🔗 Cited by

Papers of our library cite their works 4,463 times (of the 149,439 papers whose bibliographies we read); 741 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/peter-henderson/