[2008.02275] Aligning AI With Shared Human Values

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

[2008.02275] Aligning AI With Shared Human Values Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computers and Society arXiv:2008.02275 (cs) [Submitted on 5 Aug 2020 ( v1 ), last revised 17 Feb 2023 (this version, v6)] Title: Aligning AI With Shared Human Values Authors: Dan Hendrycks , Collin Burns , Steven Basart , Andrew Critch , Jerry Li , Dawn Song , Jacob Steinhardt View a PDF of the paper titled Aligning AI With Shared Human Values, by Dan Hendrycks and Collin Burns and Ste

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2405.17345] Exploring and steering the moral compass of Large Language Modelsarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2405.07987] The Platonic Representation Hypothesisarxiv.org
• [2410.02683] DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Lifearxiv.org
• [2506.00751] Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?arxiv.org
• [2503.07003] Large Language Models Often Say One Thing and Do Anotherarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2503.03750] The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systemsarxiv.org
• [2304.03279] Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkarxiv.org
• [2507.21509] Persona Vectors: Monitoring and Controlling Character Traits in Language Modelsarxiv.org
• [2602.22755] AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviorsarxiv.org