LIRE: listwise reward enhancement for preference alignment

Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo, Zhendong Mao

Abstract
Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and is widely adopted by researchers. However, implementing RLHF is complex, and its sensitivity to hyperparameters renders achieving stable performance and scalability challenging. Furthermore, prevailing approaches to preference alignment primarily concentrate on pairwise comparisons, with limited exploration into multi-response scenarios, thereby overlooking the potential richness within the candidate pool. For the above reasons, we propose a new approach: Listwise Reward Enhancement for Preference Alignment (LIRE), a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework, thus eliminating the need for online sampling during training. LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm while naturally extending to multi-response scenarios. Moreover, we introduce a self-enhancement algorithm aimed at iteratively refining the reward during training. Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks, with good transferability to out-of-distribution data, assessed using proxy reward models and human annotators.
Anthology ID:
2024.findings-acl.201
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3377–3394
Language:
URL:
https://aclanthology.org/2024.findings-acl.201
DOI:
10.18653/v1/2024.findings-acl.201
Bibkey:
Cite (ACL):
Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo, and Zhendong Mao. 2024. LIRE: listwise reward enhancement for preference alignment. In Findings of the Association for Computational Linguistics ACL 2024, pages 3377–3394, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
LIRE: listwise reward enhancement for preference alignment (Zhu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2024.findings-acl.201.pdf
PDF Search