Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Mathieu Rita, Florian Strub, Rahma Chaabouni 0001, Paul Michel, Emmanuel Dupoux, Olivier Pietquin. Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning. In Lun-Wei Ku, Andre Martins, Vivek Srikumar, editors, Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024. pages 12447-12472, Association for Computational Linguistics, 2024. [doi]

This author has not been identified. Look up 'Mathieu Rita' in GoogleThis author has not been identified. Look up 'Florian Strub' in GoogleThis author has not been identified. Look up 'Rahma Chaabouni 0001' in GoogleThis author has not been identified. Look up 'Paul Michel' in GoogleThis author has not been identified. Look up 'Emmanuel Dupoux' in GoogleThis author has not been identified. Look up 'Olivier Pietquin' in Google

runs on WebDSL