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

• URL: http://arxiv.org/abs/2605.01284v1
• Date: Sat, 02 May 2026 06:40:42 GMT
• Title: Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
• Abstract summary: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions.<n>We present textbfChain of Evidence (CoE), a retriever-agnostic visual attribution framework.
• Score: 19.889854990300595
• License: http://creativecommons.org/licenses/by/4.0/
• 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 burdened with manually locating evidence within lengthy documents based on vague text-level citations; and (2) \textit{Visual semantic loss}, where the conversion of visually rich documents (e.g., slides, PDFs with charts) into text discards spatial logic and layout cues essential for reasoning. To bridge this gap, we present \textbf{Chain of Evidence (CoE)}, a retriever-agnostic visual attribution framework that leverages Vision-Language Models to reason directly over screenshots of retrieved document candidates. CoE eliminates format-specific parsing and outputs precise bounding boxes, visualizing the complete reasoning chain within the retrieved candidate set. We evaluate CoE on two distinct benchmarks: \textbf{Wiki-CoE}, a large-scale dataset of structured web pages derived from 2WikiMultiHopQA, and \textbf{SlideVQA}, a challenging dataset of presentation slides featuring complex diagrams and free-form layouts. Experiments demonstrate that fine-tuned Qwen3-VL-8B-Instruct achieves robust performance, significantly outperforming text-based baselines in scenarios requiring visual layout understanding, while establishing a retriever-agnostic solution for pixel-level interpretable iRAG. Our code is available at https://github.com/PeiYangLiu/CoE.git.

Related papers

• ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval [62.80735412748694]
  ConceptFormer is a latent concept representation learning framework for visual document retrieval.<n>It query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance.<n>It achieves 16.7% and 22.1% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively.
  arXiv  Detail & Related papers  (2026-08-16T12:07:12Z)
• Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering [2.6264656632831667]
  DualGraph represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject--predicate--object triples.<n>We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types.
  arXiv  Detail & Related papers  (2026-05-26T15:22:42Z)
• MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing [74.84107522458798]
  MPDocBench-Parse is a benchmark for multi-page document parsing in real-world applications.<n>It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles.
  arXiv  Detail & Related papers  (2026-05-21T07:36:41Z)
• Lightweight and Production-Ready PDF Visual Element Parsing [0.0]
  Existing PDFs often miss complex visuals, extract non-informative artifacts, produce fragmented elements, and fail to reliably associate captions with their corresponding elements.<n>We present a lightweight and production level PDF parsing framework that can accurately detect visual elements and associates captions.
  arXiv  Detail & Related papers  (2026-04-25T12:40:13Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow.<n>We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• Multimodal OCR: Parse Anything from Documents [72.69545534962234]
  dots.mocr treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets.<n>It reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction.<n>It supports end-to-end training over heterogeneous document elements.
  arXiv  Detail & Related papers  (2026-03-13T14:42:21Z)
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA [53.491241153213565]
  $G2$-Reader is a dual-graph system for multimodal question answering.<n>$G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)<n>On VisDoMBench across five multimodal domains, $G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)
  arXiv  Detail & Related papers  (2026-01-29T17:52:54Z)
• Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding [35.429403152845836]
  Youtu-Parsing is an efficient and versatile document parsing model designed for high-performance content extraction.<n>The model exhibits strong robustness when handling rare characters, multilingual text, and handwritten content.<n>Youtu-Parsing achieves state-of-the-art (SOTA) performance on the OmniDocBench and olmOCR-bench benchmarks.
  arXiv  Detail & Related papers  (2026-01-28T09:37:13Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval [22.33550491040999]
  RAG grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents.<n>We build two plug-and-play retrievers: StatementGraphRAG and TopicGraphRAG.<n>Our methods outperform naive chunk-based RAG achieving an average relative improvement of 23.1% in retrieval recall and correctness.
  arXiv  Detail & Related papers  (2025-06-09T17:58:35Z)
• Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding [42.506971197471195]
  We introduce two fine-grained structured datasets: DocMark-Pile, comprising approximately 3.8M pretraining data pairs for document parsing, and DocMark-Instruct, featuring 624k fine-tuning data annotations for grounded instruction following.<n>Our proposed model significantly outperforms existing state-of-theart MLLMs across a range of visual document understanding benchmarks.
  arXiv  Detail & Related papers  (2025-05-08T17:37:36Z)
• OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition [79.852642726105]
  We propose a unified paradigm for parsing visually-situated text across diverse scenarios. Specifically, we devise a universal model, called Omni, which can simultaneously handle three typical visually-situated text parsing tasks. In Omni, all tasks share the unified encoder-decoder architecture, the unified objective point-conditioned text generation, and the unified input representation.
  arXiv  Detail & Related papers  (2024-03-28T03:51:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.