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

arXiv: https://arxiv.org/abs/2605.01284 · HTML: https://mlsanity.com/paper/2605.01284/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 2 May 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 34)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering](https://mlsanity.com/paper/2404.04302/) (2024)
- [Chain-of-Retrieval Augmented Generation](https://mlsanity.com/paper/2501.14342/) (2025)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation](https://mlsanity.com/paper/2406.19215/) (2024)
- [Source-Aware Training Enables Knowledge Attribution in Language Models](https://mlsanity.com/paper/2404.01019/) (2024)
- [VISA: Retrieval Augmented Generation with Visual Source Attribution](https://mlsanity.com/paper/2412.14457/) (2024)
- [INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval](https://mlsanity.com/paper/2604.18051/) (2026)
- [A Survey on Efficient Vision-Language Models](https://mlsanity.com/paper/2504.09724/) (2025)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network](https://mlsanity.com/paper/2603.26341/) (2026)
- [Queries Are Not Alone: Clustering Text Embeddings for Video Search](https://mlsanity.com/paper/2510.07720/) (2025)
- [KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.18397/) (2025)
- [Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG](https://mlsanity.com/paper/2511.09980/) (2025)
- [Masked Diffusion for Generative Recommendation](https://mlsanity.com/paper/2511.23021/) (2025)
- [Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning](https://mlsanity.com/paper/2604.11407/) (2026)
- [Data Selection for Multi-turn Dialogue Instruction Tuning](https://mlsanity.com/paper/2604.07892/) (2026)

## Abstract (arXiv)

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) textitCoarse-grained attribution, where users are burdened with manually locating evidence within lengthy documents based on vague text-level citations; and (2) textitVisual 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 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: Wiki-CoE, a large-scale dataset of structured web pages derived from 2WikiMultiHopQA, and 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.