[2510.07686] Stress-Testing Model Specs Reveals Character Differences among Language Models

YOU make open access possible! Tell us why you support #openaccess and give to arXiv this week to help keep science open for all. Help | Advanced Search 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

[2510.07686] Stress-Testing Model Specs Reveals Character Differences among Language Models 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:2510.07686 (cs) [Submitted on 9 Oct 2025 ( v1 ), last revised 23 Oct 2025 (this version, v2)] Title: Stress-Testing Model Specs Reveals Character Differences among Language Models Authors: Jifan Zhang , Henry Sleight , Andi Peng , John Schulman , Esin Durmus View a PDF of the paper titled Stress-Testing Model Spec

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2507.06187] The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gainsarxiv.org
• Stress-testing model specs reveals character differences among language modelsalignment.anthropic.com
• [2503.10965] Auditing language models for hidden objectivesarxiv.org
• Self-Adapting Language Modelsarxiv.org
• [2503.07003] Large Language Models Often Say One Thing and Do Anotherarxiv.org
• [2506.00751] Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?arxiv.org
• [2512.19428] Attention Is Not What You Needarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2407.12856] AI-AI Bias: large language models favor communications generated by large language modelsarxiv.org