Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma 0001. Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 10554-10583, Association for Computational Linguistics, 2026. [doi]

Abstract

Abstract is missing.