Training for Alignment
econ.TH
Submitted: 2026-10-26
Updated: 2026-10-26
Related papers
- Rewarding Noise: Incentives in Decentralized A/B Testing
- Rational Learning One Step Off the Path
- A polyhedral characterization of worker-quasi-stable matchings
- Information Design for Differential Privacy
- Dynamic Mechanism and Information Design in AI-Agent Environments: A General Analytical Framework
- Rationalizable Behavior in Matching with Externalities