Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Pankayaraj Pathmanathan, Furong Huang. Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 9230-9263, Association for Computational Linguistics, 2026. [doi]

This author has not been identified. Look up 'Pankayaraj Pathmanathan' in GoogleThis author has not been identified. Look up 'Furong Huang' in Google

runs on WebDSL