Icon2: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation. | OpenReview

Icon2: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation.

Qiyuan Chen 0003, Hongsen Huang, Qian Shao, Jiahe Chen, Jintai Chen, Hongxia Xu, Renjie Hua, Ren Chuan, Jian Wu 0001

23 Dec 2025 (modified: 06 Jan 2026)CoRR 2025EveryoneRevisionsCC BY-SA 4.0

Loading