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]
@inproceedings{RitaS0MDP24,
title = {Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning},
author = {Mathieu Rita and Florian Strub and Rahma Chaabouni 0001 and Paul Michel and Emmanuel Dupoux and Olivier Pietquin},
year = {2024},
url = {https://aclanthology.org/2024.findings-acl.740},
researchr = {https://researchr.org/publication/RitaS0MDP24},
cites = {0},
citedby = {0},
pages = {12447-12472},
booktitle = {Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024},
editor = {Lun-Wei Ku and Andre Martins and Vivek Srikumar},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-099-8},
}