Evans, Owain

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Lin, S., Hilton, J., & Evans, O. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Misinformation and Its ImpactsTopic Modeling

Cited by 904

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Lin, S., Hilton, J., & Evans, O. (2021) · arXiv

Misinformation and Its ImpactsTopic Modeling

Cited by 899

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., et al. (2018) · arXiv

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 849

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., et al. (2018) · Apollo - University of Cambridge Repository

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 849

Viewpoint: when will AI exceed human performance? evidence from AI experts

Grace, K., Salvatier, J., Dafoe, A., Zhang, B., & Evans, O. (2018) · Journal of Artificial Intelligence Research

Artificial Intelligence ApplicationsEthics and Social Impacts of AI

Cited by 579

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 569

When Will AI Exceed Human Performance? Evidence from AI Experts

Grace, K., Salvatier, J., Dafoe, A., Zhang, B., & Evans, O. (2017) · arXiv

Artificial Intelligence ApplicationsEthics and Social Impacts of AI

Cited by 285

Teaching Models to Express Their Uncertainty in Words

Lin, S., Hilton, J., & Evans, O. (2022) · arXiv

Adversarial Robustness in Machine LearningTopic Modeling

Cited by 59

Truthful AI: Developing and governing AI that does not lie

Evans, O., Cotton-Barratt, O., Finnveden, L., Bales, A., Balwit, A., Wills, P., Righetti, L., & Saunders, W. (2021) · arXiv

Ethics and Social Impacts of AIMisinformation and Its Impacts

Cited by 39

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

Berglund, L., Tong, M., Kaufmann, M., Balesni, M., Stickland, A. C., Korbak, T., & Evans, O. (2023) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 36

Training large language models on narrow tasks can lead to broad misalignment

Betley, J., Warncke, N., Sztyber-Betley, A., Tan, D., Bao, X., Soto, M., Srivastava, M., Labenz, N., & Evans, O. (2026) · Nature

Ethics and Social Impacts of AIAdversarial Robustness in Machine Learning

Cited by 31

Looking Inward: Language Models Can Learn About Themselves by Introspection

Binder, F. J., Chua, J., Korbak, T., Sleight, H., Hughes, J., Long, R., Perez, E., Turpin, M., & Evans, O. (2024) · arXiv

Explainable Artificial Intelligence (XAI)Philosophy and Theoretical Science

Cited by 20

Taken out of context: On measuring situational awareness in LLMs

Berglund, L., Stickland, A. C., Balesni, M., Kaufmann, M., Tong, M., Korbak, T., Kokotajlo, D., & Evans, O. (2023) · arXiv

Topic ModelingAdversarial Robustness in Machine Learning

Cited by 8

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Laine, R., Chughtai, B., Betley, J., Hariharan, K., Scheurer, J., Balesni, M., Hobbhahn, M., Meinke, A., & Evans, O. (2024) · arXiv

Topic ModelingEthics and Social Impacts of AI

Cited by 8

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Laine, R., Chughtai, B., Betley, J., Hariharan, K., Scheurer, J., Balesni, M., Hobbhahn, M., Meinke, A., & Evans, O. (2024) · Advances in Neural Information Processing Systems 37

Topic ModelingEthics and Social Impacts of AI

Cited by 8

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Betley, J., Tan, D., Warncke, N., Sztyber-Betley, A., Bao, X., Soto, M., Labenz, N., & Evans, O. (2025) · arXiv

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 7

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Chen, R., Arditi, A., Sleight, H., Evans, O., & Lindsey, J. (2025) · arXiv

Ethics and Social Impacts of AITopic Modeling

Cited by 7

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Treutlein, J., Choi, D., Betley, J., Marks, S., Anil, C., Grosse, R., & Evans, O. (2024) · arXiv

Topic ModelingMultimodal Machine Learning Applications

Cited by 6

Are DeepSeek R1 And Other Reasoning Models More Faithful?

Chua, J., & Evans, O. (2025) · arXiv

Explainable Artificial Intelligence (XAI)Topic Modeling

Cited by 1

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Chua, J., Betley, J., Taylor, M., & Evans, O. (2025) · arXiv

Adversarial Robustness in Machine LearningEthics and Social Impacts of AI

Cited by 1

Tell, don't show: Declarative facts influence how LLMs generalize

Meinke, A., & Evans, O. (2023) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 0

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Taylor, M., Chua, J., Betley, J., Treutlein, J., & Evans, O. (2025) · arXiv

Ethics and Social Impacts of AIAdversarial Robustness in Machine Learning

Cited by 0