conftrace_

reward ambiguity

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

policy deception (1) multi-agent system (1) structured generation (1) deceptive behavior (1) boltzmann rationality (1) deceptive inflation (1) table-to-latex generation (1) component-specific optimization (1) human feedback (1) partial observability (1)

Papers

CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation ACL 2026 When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback NeurIPS 2024