🧑‍🔬 Ethan Perez — all works

33 works · ← Ethan Perez

1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksarXiv:2005.11401Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al.2020 · 6,256 citations
2. Language Models (Mostly) Know What They Know ↗arXiv:2207.05221 · no summary yetSaurav Kadavath et al.2022 · 827 citations
3. Red Teaming Language Models with Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Saffron Huang, Francis Song, et al.2022 · 700 citations
4. ELI5: Long Form Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL)Angela Fan, Yacine Jernite, Ethan Perez, et al.2019 · 695 citations
5. Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought PromptingConference on Neural Information Processing Systems (NeurIPS)Miles Turpin, Julian Michael, Ethan Perez, et al.2023 · 586 citations
6. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedarXiv:2209.07858Deep Ganguli, Liane Lovitt, Jackson Kernion, et al.2022 · 485 citations
7. True Few-Shot Learning with Language ModelsarXiv:2105.11447Ethan Perez, Douwe Kiela, Kyunghyun Cho2021 · 412 citations
8. FiLM: Visual Reasoning with a General Conditioning LayerarXiv:1709.07871Ethan Perez, Florian Strub, Harm de Vries, et al.2017 · 400 citations
9. Discovering Language Model Behaviors with Model-Written EvaluationsarXiv:2212.09251Ethan Perez, Sam Ringer, Kamilė Lukošiūtė, et al.2022 · 328 citations
10. Unsupervised Question Decomposition for Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Patrick Lewis, Wen-tau Yih, et al.2020 · 222 citations
11. Case-based Reasoning for Natural Language Queries over Knowledge Bases ↗Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yetRajarshi Das et al.2021 · 201 citations
12. Pretraining Language Models with Human PreferencesarXiv:2302.08582Tomasz Korbak, Kejian Shi, Angelica Chen, et al.2023 · 121 citations
13. Measuring Progress on Scalable Oversight for Large Language ModelsarXiv:2211.03540Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez, et al.2022 · 117 citations
14. Studying Large Language Model Generalization with Influence FunctionsarXiv:2308.03296Roger Grosse, Juhan Bae, Cem Anil, et al.2023 · 105 citations
15. Debating with More Persuasive LLMs Leads to More Truthful AnswersarXiv:2402.06782Akbir Khan, John Hughes, Dan Valentine, et al.2024 · 101 citations
16. Training Language Models with Language Feedback at Scale ↗arXiv:2303.16755 · no summary yetJérémy Scheurer et al.2023 · 85 citations
17. Alignment faking in large language models ↗arXiv (Cornell University) · no summary yetRyan Greenblatt et al.2024 · 82 citations
18. Question Decomposition Improves the Faithfulness of Model-Generated Reasoning ↗arXiv (Cornell University) · no summary yetAnsh Radhakrishnan et al.2023 · 74 citations
19. Training Language Models with Language Feedback ↗arXiv (Cornell University) · no summary yetJérémy Scheurer et al.2022 · 58 citations
20. Improving Code Generation by Training with Natural Language Feedback ↗arXiv:2303.16749 · no summary yetAngelica Chen et al.2023 · 47 citations
21. Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models ↗arXiv (Cornell University) · no summary yetCarson Denison et al.2024 · 46 citations
22. Finding Generalizable Evidence by Learning to Convince Q&A ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Siddharth Karamcheti, Rob Fergus, et al.2019 · 43 citations
23. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗arXiv (Cornell University) · no summary yetTomek Korbak et al.2025 · 35 citations
24. Language Models Learn to Mislead Humans via RLHF ↗arXiv (Cornell University) · no summary yetJiaxin Wen et al.2024 · 33 citations
25. Specific versus General Principles for Constitutional AI ↗arXiv (Cornell University) · no summary yetSandipan Kundu et al.2023 · 28 citations
26. Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ↗arXiv (Cornell University) · no summary yetEthan Perez, Douwe Kiela, Kyunghyun Cho2021 · 22 citations
27. Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions ↗Proceedings of the First Workshop on Learning with Natural Language Supervision · no summary yetAlicia Parrish et al.2022 · 13 citations
28. Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought ↗arXiv (Cornell University) · no summary yetJames Chua et al.2024 · 10 citations
29. Sabotage Evaluations for Frontier Models ↗arXiv (Cornell University) · no summary yetJoe Benton et al.2024 · 7 citations
30. Forecasting Rare Language Model Behaviors ↗arXiv (Cornell University) · no summary yetErik Jones et al.2025 · 3 citations
31. Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks ↗arXiv (Cornell University) · no summary yetHoagy Cunningham et al.2026 · 2 citations
32. Unsupervised Elicitation of Language Models ↗arXiv (Cornell University) · no summary yetJiaxin Wen et al.2025 · 2 citations
33. Quantifying Elicitation of Latent Capabilities in Language Models ↗neural information processing systems · no summary yetElizabeth Donoway et al.2025 · 1 citation

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ethan-perez/works/