Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning

• URL: http://arxiv.org/abs/2511.12003v1
• Date: Sat, 15 Nov 2025 02:50:23 GMT
• Title: Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
• Abstract summary: Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
• Score: 55.232400251303794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aiming to identify precise evidence sources from visual documents, visual evidence attribution for visual document retrieval-augmented generation (VD-RAG) ensures reliable and verifiable predictions from vision-language models (VLMs) in multimodal question answering. Most existing methods adopt end-to-end training to facilitate intuitive answer verification. However, they lack fine-grained supervision and progressive traceability throughout the reasoning process. In this paper, we introduce the Chain-of-Evidence (CoE) paradigm for VD-RAG. CoE unifies Chain-of-Thought (CoT) reasoning and visual evidence attribution by grounding reference elements in reasoning steps to specific regions with bounding boxes and page indexes. To enable VLMs to generate such evidence-grounded reasoning, we propose Look As You Think (LAT), a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution. During training, LAT evaluates the attribution consistency of each evidence region and provides rewards only when the CoE trajectory yields correct answers, encouraging process-level self-verification. Experiments on vanilla Qwen2.5-VL-7B-Instruct with Paper- and Wiki-VISA benchmarks show that LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5. Meanwhile, LAT not only outperforms the supervised fine-tuning baseline, which is trained to directly produce answers with attribution, but also exhibits stronger generalization across domains.

Related papers

• V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning [59.47823383593251]
  Vision-sampling models can produce fluent answers that are insufficiently grounded in the visual evidence.<n>We introduce Visuals-Based Reinforcement Learning, which decomposes reference responses into atomic propositions.<n>We train our model based on the same SFT checkpoint using component-wise, prefix-localized rubric credit.
  arXiv  Detail & Related papers  (2026-08-26T09:40:46Z)
• Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation [23.254574194880234]
  Fake news increasingly relies on cross-modal image-text forgeries.<n>Existing methods produce black-box detection results without any decision rationale.<n>We propose a multi-modal manipulation detector based on an Evidence-Grounded Forensic Reasoning framework.
  arXiv  Detail & Related papers  (2026-08-08T08:41:26Z)
• MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering [73.47440561592556]
  We introduce MultAttnAttrib, a training-free attribution-generation method.<n>We show that MultAttnAttrib consistently outperforms a variety of attribution-generation methods.<n>Our method produces attributions at up to one-seventh of the direct inference latency compared to prompting.
  arXiv  Detail & Related papers  (2026-07-01T19:29:19Z)
• VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought [16.361394107862502]
  We propose the Visual Grounding Chain-of-Thought dataset, which explicitly links each reasoning step to real visual evidence within the image.<n>The pipeline generates step-by-step grounded reasoning with GPT-4o and refines the grounding through a rationale-driven open-set detection process.<n> Experiments with representative LVLMs, including LLaVA-1.5 and Qwen2-VL, demonstrate consistent improvements on most evaluation metrics.
  arXiv  Detail & Related papers  (2026-04-23T08:04:07Z)
• Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models [53.279391576560755]
  Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and limitation.<n>This poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount.<n>We introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs.
  arXiv  Detail & Related papers  (2026-04-23T01:37:50Z)
• Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning [17.78591587115095]
  We introduce Reinforce to Learn, Elect to Reason (RLER), a dual paradigm that decouples learning to produce evidence from obtaining a reliable answer.<n>RLER achieves state of the art across all benchmarks and delivers an average improvement of 6.3% over base models.
  arXiv  Detail & Related papers  (2026-04-06T03:01:52Z)
• See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs [24.90876091319589]
  We present an iterative, training-free, plug-and-play framework for visually-grounded multimodal reasoning.<n>Our key idea is to supervise each reasoning step at test time with visual evidence.<n>Our method achieves 16.5%-29.5% improvements on TreeBench and 13.7% RH-AUC gains on RH-Bench.
  arXiv  Detail & Related papers  (2026-02-25T02:13:59Z)
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning [29.78411369746505]
  PEARL is a dual-branch, perception-reasoning synergistic that strengthens multimodal reasoning by explicitly anchoring it to verified visual evidence.<n>PEARL achieves substantial gains on multimodal reasoning benchmarks, e.g., a +9.7% improvement over the baseline and +6.6% over GRPO on MathVerse.
  arXiv  Detail & Related papers  (2025-11-23T13:15:58Z)
• Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises [0.0]
  We propose a framework that integrates abductive inference into retrieval-augmented LLMs.<n> Experimental results on abductive reasoning and multi-hop QA benchmarks show that our approach improves both answer accuracy and reasoning faithfulness.<n>This work highlights abductive inference as a promising direction for enhancing the robustness and explainability of RAG systems.
  arXiv  Detail & Related papers  (2025-11-06T03:37:24Z)
• VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation [64.82775032985485]
  Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations.<n>Yet current VRAG systems often fail to reliably perceive and integrate evidence across multiple images, leading to weak grounding and erroneous conclusions.<n>We propose EVisRAG, an end-to-end framework that learns to reason with evidence-guided multi-image to address this issue.
  arXiv  Detail & Related papers  (2025-10-10T13:34:23Z)
• Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning [53.05161493434908]
  Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes.<n>We introduce Veri-R1, an online reinforcement learning framework that enables an LLM to interact with a search engine and to receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors.<n> Empirical results show that Veri-R1 improves joint accuracy by up to 30% and doubles the evidence score, often surpassing its larger-scale model counterparts.
  arXiv  Detail & Related papers  (2025-10-02T11:49:48Z)
• CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding [1.6257248483123767]
  We present textbfCoRGI(textbfChain textbfof textbfReasoning with textbfGrounded textbfInsights), a framework that enhances reasoning reliability through post-hoc verification of chain-of-thought outputs.
  arXiv  Detail & Related papers  (2025-08-01T07:17:12Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification [118.03466985807331]
  We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.<n>We introduce the feedback-based evidence retriever(FER) that optimize the evidence retrieval process by incorporating feedback from the claim verifier.
  arXiv  Detail & Related papers  (2023-10-18T02:59:38Z)

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.