作者位次 #4/5ACL 2026Findings· Findings of ACL
Trident: Self-Supervised Preference Alignment via Triplet Regularization
Yingnan Guo · Kejia Chen · Xiaofeng Zhang · Zifei Wu · Yu Zhang
摘要
Aligning Large Vision-Language Models (LVLMs) to mitigate hallucinations typically relies on high-quality preference data. However, in self-supervised settings, standard binary preference optimization (e.g., DPO) suffers from noisy supervision and semantic ambiguity, as automatically generated ch...