Reasoning Models Don't Always Say What They Thinkwith Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato +101 versionW_sgh3nvvuv1 · current
Unsupervised Elicitation of Language ModelsJiaxin Wen, Zachary Ankner, Arushi Somani et al.0 citations2506.10139v22025arXiv
Reasoning Models Don't Always Say What They ThinkYanda Chen, Joe Benton, Ansh Radhakrishnan et al.17 citations2505.05410v12025arXivon Valency
Values in the Wild: Discovering and Analyzing Values in Real-World Language Model InteractionsSaffron Huang, Esin Durmus, Miles McCain et al.2 citations2504.15236v12025arXiv