Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?

Kexin Huang; Junkang Wu; Ziqian Chen; xue wang; Jinyang Gao; Bolin Ding; Jiancan Wu; Xiangnan He; Xiang Wang

2025 ICML ICML 2025

Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Kexin Huang, Junkang Wu, Ziqian Chen, xue wang, Jinyang Gao, Bolin Ding, Jiancan Wu, Xiangnan He, Xiang Wang

Topics

Machine Learning > Optimization & Theory > Optimization Natural Language Processing > Resources & Methods > Large Language Models Artificial Intelligence > Core AI > Large Language Models

Keywords

preference learning reward margin implicit reward margin alignment potential explicit reward margin self-play data generation

Download PDF