Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation 文章

ArXiv CS.CV2026-05-26NEWSen作者: Peiyang Liu, Ziqiang Cui, Xi Wang, Di Liang, Wei Ye
大语言模型
查看原文 →
关系图谱

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation · 相关技术

相关技术

Retrieval-augmented generationODEPLAlanguage model递归自我改进evalVLMTeraStraight-Through EstimatorSSESPASEMReferring expression comprehension (REC)Vision-Language ModelsHISGrouped Memorization EvaluationGranular Alignment ParadigmForEffort Metric AttentionANN