---
title: "Peter Henderson — all works — Elamur Research"
description: "All 36 works of Peter Henderson in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/peter-henderson/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/peter-henderson/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Peter Henderson](https://md.research.elamur.ai/free/en/authors/peter-henderson/) / all works

# Peter Henderson — all works

36 works · [← Peter Henderson](https://md.research.elamur.ai/free/en/authors/peter-henderson/)

1. **[BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗](https://arxiv.org/abs/2211.05100) arXiv:2211.05100 · no summary yet**BigScience Workshop et al.*2022 · 1,606 citations*
2. **[Holistic Evaluation of Language Models ↗](https://arxiv.org/abs/2211.09110) arXiv:2211.09110 · Published in Transactions on Machine Learning Research (TMLR), 2023 · no summary yet**Percy Liang et al.*2022 · 1,001 citations*
3. [**Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! arXiv:2310.03693**Xiangyu Qi, Yi Zeng, Tinghao Xie, et al.*2023 · 355 citations*](https://md.research.elamur.ai/free/en/papers/qi-2023-fine-tuning-aligned-language-models/)
4. **[Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims ↗](https://arxiv.org/abs/2004.07213) arXiv:2004.07213 · no summary yet**Miles Brundage et al.*2020 · 320 citations*
5. **[Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning ↗](https://arxiv.org/abs/2002.05651) arXiv (Cornell University) · no summary yet**Peter B. Henderson et al.*2020 · 258 citations*
6. **[Visual Adversarial Examples Jailbreak Aligned Large Language Models ↗](https://arxiv.org/abs/2306.13213) arXiv:2306.13213 · no summary yet**Xiangyu Qi et al.*2023 · 240 citations*
7. **[With Little Power Comes Great Responsibility ↗](https://aclanthology.org/2020.emnlp-main.745/) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Dallas Card et al.*2020 · 173 citations*
8. **[Foundation Models and Fair Use ↗](https://doi.org/10.2139/ssrn.4404340) SSRN Electronic Journal · no summary yet**Peter B. Henderson et al.*2023 · 134 citations*
9. **[When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset ↗](https://arxiv.org/abs/2104.08671) arXiv:2104.08671 · no summary yet**Lucia Zheng et al.*2021 · 134 citations*
10. **[Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset ↗](https://arxiv.org/abs/2207.00220) arXiv:2207.00220 · no summary yet**Peter Henderson et al.*2022 · 133 citations*
11. **[Safety Alignment Should Be Made More Than Just a Few Tokens Deep ↗](https://arxiv.org/abs/2406.05946) arXiv:2406.05946 · no summary yet**Xiangyu Qi et al.*2024 · 97 citations*
12. **[SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ↗](https://arxiv.org/abs/2406.14598) arXiv:2406.14598 · no summary yet**Tinghao Xie et al.*2024 · 87 citations*
13. **[Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ↗](https://arxiv.org/abs/2402.05162) arXiv:2402.05162 · no summary yet**Boyi Wei et al.*2024 · 66 citations*
14. [**A Reasoning-Focused Legal Retrieval Benchmark arXiv:2505.03970**Lucia Zheng, Neel Guha, Javokhir Arifov, et al.*2025 · 55 citations*](https://md.research.elamur.ai/free/en/papers/zheng-2025-reasoning-focused-legal-retrieval-benchmark/)
15. **[Promises and pitfalls of artificial intelligence for legal applications ↗](https://arxiv.org/abs/2402.01656) arXiv:2402.01656 · no summary yet**Sayash Kapoor, Peter Henderson, Arvind Narayanan*2024 · 40 citations*
16. **[Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models ↗](https://doi.org/10.1145/3600211.3604690) Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yet**Peter B. Henderson et al.*2023 · 36 citations*
17. **[On the Societal Impact of Open Foundation Models ↗](https://arxiv.org/abs/2403.07918) arXiv (Cornell University) · no summary yet**Sayash Kapoor et al.*2024 · 30 citations*
18. **[Evaluating Copyright Takedown Methods for Language Models ↗](https://doi.org/10.52202/079017-4415) neural information processing systems · no summary yet**Boyi Wei et al.*2024 · 25 citations*
19. **[A Safe Harbor for AI Evaluation and Red Teaming ↗](https://arxiv.org/abs/2403.04893) arXiv (Cornell University) · no summary yet**Shayne Longpre et al.*2024 · 22 citations*
20. **[LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain ↗](https://aclanthology.org/2025.findings-naacl.7/) Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yet**Joel Niklaus et al.*2025 · 12 citations*
21. **[Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation ↗](https://arxiv.org/abs/2510.11977) arXiv:2510.11977 · no summary yet**Sayash Kapoor et al.*2025 · 11 citations*
22. **[The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources ↗](https://arxiv.org/abs/2406.16746) arXiv (Cornell University) · no summary yet**Shayne Longpre et al.*2024 · 11 citations*
23. **[Fantastic Copyrighted Beasts and How (Not) to Generate Them ↗](https://arxiv.org/abs/2406.14526) arXiv (Cornell University) · no summary yet**Luxi He et al.*2024 · 9 citations*
24. **[Position: On the Societal Impact of Open Foundation Models ↗](https://openalex.org/W7135318688) ANU Open Research (Australian National University) · no summary yet**Sayash Kapoor et al.*2024 · 6 citations*
25. **[Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs ↗](https://arxiv.org/abs/2305.02440) arXiv (Cornell University) · no summary yet**Deepak Narayanan et al.*2023 · 6 citations*
26. **[Who Checks the Citations? Benchmarking Legal Hallucination Detection ↗](https://arxiv.org/abs/2606.21155) arXiv:2606.21155 · no summary yet**Patty Liu, Dominik Stammbach, Peter Henderson*2026 · 3 citations*
27. **[Statutory Construction and Interpretation for Artificial Intelligence ↗](https://arxiv.org/abs/2509.01186) arXiv:2509.01186 · no summary yet**Luxi He et al.*2025 · 3 citations*
28. **[AI for Scaling Legal Reform: Mapping and Redacting Racial Covenants in Santa Clara County ↗](https://arxiv.org/abs/2503.03888) arXiv:2503.03888 · no summary yet**Faiz Surani et al.*2025 · 3 citations*
29. **[AI Risk Management Should Incorporate Both Safety and Security ↗](https://arxiv.org/abs/2405.19524) arXiv (Cornell University) · no summary yet**Xiangyu Qi et al.*2024 · 3 citations*
30. **[Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models ↗](https://doi.org/10.52202/075280-2904) neural information processing systems · no summary yet**Deepak Narayanan et al.*2023 · 3 citations*
31. **[In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI ↗](https://arxiv.org/abs/2503.16861) arXiv (Cornell University) · no summary yet**Shayne Longpre et al.*2025 · 2 citations*
32. **[The Mirage of Artificial Intelligence Terms of Use Restrictions ↗](https://arxiv.org/abs/2412.07066) arXiv:2412.07066 · no summary yet**Peter Henderson, Mark A. Lemley*2024 · 2 citations*
33. **[Statutory construction and interpretation for AI ↗](https://doi.org/10.1073/pnas.2509766123) Proceedings of the National Academy of Sciences · no summary yet**Luxi He et al.*2026 · 1 citation*
34. **[The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege ↗](https://doi.org/10.1609/aies.v8i2.36625) Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yet**Luxi He et al.*2025 · 1 citation*
35. **[Legal Domain Adaptation of Modern BERT Models ↗](https://arxiv.org/abs/2606.28538) arXiv:2606.28538 · no summary yet**Dominik Stammbach, Peter Henderson*2026*
36. **[A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection ↗](https://doi.org/10.52202/085713-2956) neural information processing systems · no summary yet**Gaku Morio et al.*2025*