Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

[2509.22415] Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2509.22415 (cs) [Submitted on 26 Sep 2025 ( v1 ), last revised 15 Aug 2026 (this version, v5)] Title: Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Authors: Jiawei Liang , Jianjie Huang , Xianghao Jiao , Siyuan Liang , Shiming Liu , Xiaochun Cao View a PDF of the paper titled Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models, by Jiawei Liang and 5 other authors View PDF HTML (experimental) Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect. Recent logit-lens attribution methods project each visual-token hidden state into the vocabulary space to explain generated words, but this token-wise readout introduces a mismatch: visual tokens are context-mixed by the model, while the attribution score is decoded independently at each token location. This often produces fragmented attribution maps and can be further affected by autoregressive context signals from preceding text tokens. We propose ERCR, an attribution framework built from Evidence Recomposition (ER) and Predictive Context Residualization (PCR). ER aggregates target evidence across multiple views with different token-to-region assignments, reducing attribution fragmentation caused by a single readout grid. PCR estimates a preceding-token context map with RBO-based rank relevance and subtracts its fitted component from the ER map to suppress context-token interference. Experiments on LLaVA, Qwen2-VL, and InternVL families across COCO Caption, GranDf, and OpenPSG show that ERCR improves visual evidence for target tokens and mitigates preceding-token context interference under the existing evaluation protocol. On Qwen2-VL-2B, ERCR improves TAM F1-IoU from 39.10 to 44.45 on COCO Caption and from 30.83 to 37.20 on GranDf. Overall, ERCR provides a practical refinement for token-level visual evidence inspection. Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2509.22415 [cs.CV] (or arXiv:2509.22415v5 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2509.22415 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Siyuan Liang [ view email ] [v1] Fri, 26 Sep 2025 14:39:13 UTC (13,625 KB) [v2] Wed, 1 Oct 2025 16:48:01 UTC (13,624 KB) [v3] Tue, 14 Jul 2026 04:34:18 UTC (12,637 KB) [v4] Wed, 15 Jul 2026 06:42:59 UTC (12,637 KB) [v5] Sat, 15 Aug 2026 09:44:07 UTC (12,637 KB) Full-text links: Access Paper: View a PDF of the paper titled Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models, by Jiawei Liang and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-09 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Information Theoretic Adversarial Training of Large Language Models#160754
• MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models#1061443
• Optimization inspired few-shot adaptation for Large Language Models#211625
• LaMI: Augmenting Large Language Models via Late Multi-Image Fusion#139076
• One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models#1130943