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

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation arXiv:2605.01284v2 Announce Type: replace Abstract: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external documents. However, current systems predominantly operate on parsed text, which creates two critical bottlenecks: (1) \textit{Coarse-grained attribution}, where users are