Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models.

Anthony GX-Chen

Ayush Rajesh Jhaveri Anthony GX-Chen Ilia Sucholutsky Eunsol Choi Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models. 2026 April abs/2604.02485 CoRR https://doi.org/10.48550/arXiv.2604.02485 db/journals/corr/corr2604.html#abs-2604-02485 streams/journals/corr

Anthony GX-Chen Ankit Anand Gheorghe Comanici Zaheer Abbas Eser Aygün David Smalling Shibl Mourad Doina Precup André Barreto 0001 Mark Rowland 0001 Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning. 2026 June abs/2606.03962 CoRR https://doi.org/10.48550/arXiv.2606.03962 db/journals/corr/corr2606.html#abs-2606-03962 streams/journals/corr

Mandana Samiei Eunice Yiu Anthony GX-Chen Dongyan Lin Jocelyn Shen Blake A. Richards Alison Gopnik Doina Precup Human Adults and LLMs as Scientists: Who Benefits from Active Exploration? 2026 June abs/2606.06464 CoRR https://doi.org/10.48550/arXiv.2606.06464 db/journals/corr/corr2606.html#abs-2606-06464 streams/journals/corr

Anthony GX-Chen Kenneth Marino Rob Fergus Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction. 2025 ICLR https://openreview.net/forum?id=hgwGi81ndj conf/iclr/2025 db/conf/iclr/iclr2025.html#GX-ChenMF25

Anthony GX-Chen Dongyan Lin Mandana Samiei Doina Precup Blake A. Richards Rob Fergus Kenneth Marino Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists? 2025 May abs/2505.09614 CoRR https://doi.org/10.48550/arXiv.2505.09614 db/journals/corr/corr2505.html#abs-2505-09614 streams/journals/corr

Anthony GX-Chen Jatin Prakash Jeff Guo Rob Fergus Rajesh Ranganath KL-Regularized Reinforcement Learning is Designed to Mode Collapse. 2025 October abs/2510.20817 CoRR https://doi.org/10.48550/arXiv.2510.20817 db/journals/corr/corr2510.html#abs-2510-20817 streams/journals/corr

Wancong Zhang Anthony GX-Chen Vlad Sobal Yann LeCun Nicolas Carion Light-weight Probing of Unsupervised Representations for Reinforcement Learning. 1924-1949 2024 RLJ 4 db/journals/rlj/rlj4.html#ZhangGSLC24 https://rlj.cs.umass.edu/2024/papers/Paper242.html

Anthony GX-Chen Kenneth Marino Rob Fergus Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction. 2024 abs/2408.11816 CoRR https://doi.org/10.48550/arXiv.2408.11816 db/journals/corr/corr2408.html#abs-2408-11816 streams/journals/corr

Anthony GX-Chen Veronica Chelu Blake A. Richards Joelle Pineau A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions. 6829-6837 2022 AAAI https://doi.org/10.1609/aaai.v36i6.20639 conf/aaai/2022 db/conf/aaai/aaai2022.html#GX-ChenCRP22

Anthony GX-Chen Veronica Chelu Blake A. Richards Joelle Pineau A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions. 2022 abs/2201.01836 CoRR https://arxiv.org/abs/2201.01836 db/journals/corr/corr2201.html#abs-2201-01836

Wancong Zhang Anthony GX-Chen Vlad Sobal Yann LeCun Nicolas Carion Light-weight probing of unsupervised representations for Reinforcement Learning. 2022 abs/2208.12345 CoRR https://doi.org/10.48550/arXiv.2208.12345 db/journals/corr/corr2208.html#abs-2208-12345

Zaheer Abbas Ankit Anand Eser Aygün André Barreto 0001 Nicolas Carion Veronica Chelu Eunsol Choi Gheorghe Comanici Rob Fergus Alison Gopnik Jeff Guo Ayush Rajesh Jhaveri Yann LeCun Dongyan Lin Kenneth Marino Shibl Mourad Joelle Pineau Jatin Prakash Doina Precup Rajesh Ranganath Blake A. Richards Mark Rowland 0001 Mandana Samiei Jocelyn Shen David Smalling Vlad Sobal Ilia Sucholutsky Eunice Yiu Wancong Zhang