[2502.13410] Tell Me Why: Incentivizing Explanations

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

[2502.13410] Tell Me Why: Incentivizing Explanations Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computer Science and Game Theory arXiv:2502.13410 (cs) [Submitted on 19 Feb 2025] Title: Tell Me Why: Incentivizing Explanations Authors: Siddarth Srinivasan , Ezra Karger , Michiel Bakker , Yiling Chen View a PDF of the paper titled Tell Me Why: Incentivizing Explanations, by Siddarth Srinivasan and 3 other authors View PDF HTML (experimental) Abstract: Common sense suggests that w

related reading

• Towards a scale-free theory of intelligent agencymindthefuture.info
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• Common Knowledge and Aumann’s Agreement Theoremscottaaronson.blog
• thesis_ch4.pdfcs.cmu.edu
• Rationalization — LessWronglesswrong.com
• Embedded Agency (full-text version) — LessWronglesswrong.com
• [2608.03958] A game theory for foundation models shows new paths to rational cooperation through similarity inferencearxiv.org
• Natural Deception with RL - Rajan Agarwalrajan.sh
• [1902.09469] Embedded Agencyarxiv.org
• Eight Short Studies On Excuses — LessWronglesswrong.com
• A Sketch of Good Communication — LessWronglesswrong.com
• Bengt Holmström - Prize Lecture_ Pay for Performance and Beyond.pdfeconomics.mit.edu