SPO: Self Preference Optimization with Self Regularization
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5601-5614
Abstract
Yuhao Sun, Yifan Zhang, Quandong Wang, Qinzhuo Wu, Wei Liu, Jian Luan. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.Keywords
This publication has 4 references indexed in Scilit:
- Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer2024
- SimPO: Simple Preference Optimization with a Reference-Free Reward2024
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena2023
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations2023