[2503.07003] Large Language Models Often Say One Thing and Do Another

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2503.07003] Large Language Models Often Say One Thing and Do Another Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2503.07003 (cs) [Submitted on 10 Mar 2025] Title: Large Language Models Often Say One Thing and Do Another Authors: Ruoxi Xu , Hongyu Lin , Xianpei Han , Jia Zheng , Weixiang Zhou , Le Sun , Yingfei Sun View a PDF of the paper titled Large Language Models Often Say One Thing and Do Another, by Ruoxi Xu and 6 other authors View PDF HTML

related reading

• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2506.00751] Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?arxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• [2308.07633] A Survey on Model Compression for Large Language Modelsarxiv.org
• [2503.10965] Auditing language models for hidden objectivesarxiv.org
• [2506.09501] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencearxiv.org
• [2305.04388] Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingarxiv.org
• [2305.18654] Faith and Fate: Limits of Transformers on Compositionalityarxiv.org
• [2510.07686] Stress-Testing Model Specs Reveals Character Differences among Language Modelsarxiv.org
• LLM Post-Training: A Deep Dive into Reasoning Large Language Modelsarxiv.org