document search engineers

Abstract: Document understanding is increasingly judged on where an answer comes from, scored against annotated gold locations as if each fact lived in one place. In long visual documents, a fact often lives in several places: a chart value is restated in the text, a key figure reappears in the summary. We ask how often such copies occur in standard benchmarks and what they do to evaluation. We annotate 420 questions from MMLongBench-Doc and MMDocRAG with the locations that independently establish each required fact, checked by two independent reviewers. Copies are common and often cross-modal: 19.5% of MMLongBench-Doc test questions have a strict copy outside the gold, and in 28% of MMDocRAG questions a non-gold candidate alone supplies a required fact. Single-gold scoring then fails in three predictable ways. A retriever that finds a copy is scored as a miss: page recall@1 of text and visual retrievers is underestimated by 13-24 points on questions with a cross-page copy. A model that cites a copy is scored as citing wrongly: crediting equivalent evidence reverses 11% of pairwise orderings among 65 competitive MMDocRAG systems. Masking the gold region leaves the fact available elsewhere: with a copy in the input, 41-56% of correct answers across four models survive it yet fail once every annotated instance is masked. Set-level masking with automatically found copies closes 78% of the gap to masking every annotated instance at matched granularity (three models); an unverified key-string rule lowers survival at least as far but masks three times the area. We release the annotations and redundancy-aware metrics.

Abstract: Multimodal large language models (MLLMs) have shown strong visual reasoning abilities, but knowledge-intensive visual question answering often requires external textual evidence beyond the image and the model's parametric knowledge. Existing multimodal RAG systems commonly rely on Top-$K$ retrieval or reranking, which may return redundant passages and provide limited control over whether an answer update is sufficiently supported by the retrieved evidence. We propose \textit{CLIMB}, a training-free inference-time framework for multimodal RAG. CLIMB first constructs a compact complementary evidence pool using an MMR-style objective that balances query relevance and passage-level redundancy. It then performs confidence-controlled refinement within this fixed pool: an R/E/C critic scores passages by relevance, evidence specificity, and cross-modal alignment, while an evidence-grounded confidence estimator accepts an updated answer only when the estimated confidence increases. This design provides a simple stopping criterion and reduces unnecessary refinement without modifying the underlying retriever or MLLM. Experiments on Encyclopedic-VQA and InfoSeek show that CLIMB consistently improves over retrieval-augmented multimodal baselines. Ablations further indicate that complementary pooling, critic-based scoring, and iterative confidence-controlled refinement each contribute to the final performance.