Perez, Ethan

Reasoning Models Don't Always Say What They Think

Chen, Y., Benton, J., Radhakrishnan, A., Uesato, J., Denison, C., Schulman, J., Somani, A., Hase, P., Wagner, M., Roger, F., et al. (2025) · arXiv

Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AI

Cited by 18

Training Language Models with Language Feedback at Scale

Scheurer, J., Campos, J. A., Korbak, T., Chan, J. S., Chen, A., Cho, K., & Perez, E. (2023) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 14

Debating with More Persuasive LLMs Leads to More Truthful Answers

Khan, A., Hughes, J., Valentine, D., Ruis, L., Sachan, K., Radhakrishnan, A., Grefenstette, E., Bowman, S. R., Rocktäschel, T., & Perez, E. (2024) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 13

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Denison, C., MacDiarmid, M., Barez, F., Duvenaud, D., Kravec, S., Marks, S., Schiefer, N., Soklaski, R., Tamkin, A., Kaplan, J., et al. (2024) · arXiv

Reinforcement Learning in RoboticsEthics and Social Impacts of AI

Cited by 11

Training Language Models with Language Feedback

Scheurer, J., Campos, J. A., Chan, J. S., Chen, A., Cho, K., & Perez, E. (2022) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 11

Agentic Misalignment: How LLMs Could Be Insider Threats

Lynch, A., Wright, B., Larson, C., Ritchie, S. J., Mindermann, S., Hubinger, E., Perez, E., & Troy, K. (2025) · arXiv

Ethics and Social Impacts of AICybernetics and Technology in Society

Cited by 10

RL with KL penalties is better viewed as Bayesian inference

Korbak, T., Perez, E., & Buckley, C. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022

Reinforcement Learning in RoboticsTopic Modeling

Cited by 8

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

Radhakrishnan, A., Nguyen, K., Chen, A., Chen, C., Denison, C., Hernandez, D., Durmus, E., Hubinger, E., Kernion, J., Lukošiūtė, K., et al. (2023) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 8

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Sharma, M., Tong, M., Mu, J., Wei, J., Kruthoff, J., Goodfriend, S., Ong, E., Peng, A., Agarwal, R., Anil, C., et al. (2025) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 7

Specific versus General Principles for Constitutional AI

Kundu, S., Bai, Y., Kadavath, S., Askell, A., Callahan, A., Chen, A., Goldie, A., Balwit, A., Mirhoseini, A., McLean, B., et al. (2023) · arXiv

Ethics and Social Impacts of AISpeech and dialogue systems

Cited by 7

Language Models Learn to Mislead Humans via RLHF

Wen, J., Zhong, R., Khan, A., Perez, E., Steinhardt, J., Huang, M., Bowman, S. R., He, H., & Feng, S. (2024) · arXiv

Adversarial Robustness in Machine LearningTopic Modeling

Cited by 4

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Sheshadri, A., Ewart, A., Guo, P., Lynch, A., Wu, C., Hebbar, V., Sleight, H., Stickland, A. C., Perez, E., Hadfield-Menell, D., et al. (2024) · arXiv

Adversarial Robustness in Machine LearningPrivacy-Preserving Technologies in Data

Cited by 3

Sabotage Evaluations for Frontier Models

Benton, J., Wagner, M., Christiansen, E., Anil, C., Perez, E., Srivastav, J., Durmus, E., Ganguli, D., Kravec, S., Shlegeris, B., et al. (2024) · arXiv

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 2

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Wen, J., Hebbar, V., Larson, C., Bhatt, A., Radhakrishnan, A., Sharma, M., Sleight, H., Feng, S., He, H., Perez, E., et al. (2024) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 1

Unsupervised Elicitation of Language Models

Wen, J., Ankner, Z., Somani, A., Hase, P., Marks, S., Goldman-Wetzler, J., Petrini, L., Sleight, H., Burns, C., He, H., et al. (2025) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 0

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Chua, J., Rees, E., Batra, H., Bowman, S. R., Michael, J., Perez, E., & Turpin, M. (2024) · arXiv

Topic ModelingEthics and Social Impacts of AI

Cited by 0