Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

Songyang Gao; Qiming Ge; Wei Shen; Shihan Dou; Junjie Ye; Xiao Wang; Rui Zheng; Yicheng Zou; Zhi Chen; Hang Yan; Qi Zhang; Dahua Lin

2024 ICML ICML 2024

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Songyang Gao, Qiming Ge, Wei Shen, Shihan Dou, Junjie Ye, Xiao Wang, Rui Zheng, Yicheng Zou, Zhi Chen, Hang Yan, Qi Zhang, Dahua Lin

Topics

Machine Learning > Optimization & Theory > Optimization Reinforcement Learning > Methods > Policy Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

policy optimization closed-form solution human preference single inference step divergence constraint alignment

Download PDF