层、汇点与缩放：多模态大语言模型的自适应证据选择

Computer Science > Artificial Intelligence arXiv:2609.16795 (cs) [Submitted on 15 Sep 2026] Title:Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models Authors:Zhenbin Wang, Lei Zhang, Lituan Wang, Wei Huang, Yan Wang, Zhenwei Zhang View a PDF of the paper titled Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models, by Zhenbin Wang and 5 other authors View PDF HTML (experimental) Abstract:Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved from external sources. However, MLLMs may overlook relevant evidence in both modalities, attending weakly to the textual sentences or visual regions needed for the correct answer. Recent efforts address this by highlighting retrieved text and marking visual regions before generation, but apply a fixed, one-shot policy that cannot adapt to three sources of variation: whether highlighting is necessary, how much evidence different examples require, and when different textual evidence becomes relevant as the answer unfolds. We introduce Adaptive Relevance-guided Evidence Allocation (AREA), a training-free inference-time method that formulates evidence highlighting as adaptive allocation. AREA generates a single probe token to read visual and textual relevance from fixed backbone layers, then makes three decisions: i) whether to intervene (controlled by natural attention coverage and visual sink contamination), ii) how much evidence to expose (determined by relevance entropy), and iii) when to refresh text during generation (triggered by causal context-attention peaks). Across four KB-VQA and seven standard multimodal benchmarks with nine frozen MLLM checkpoints, establishes the best performance among training-free highlighting methods. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2609.16795 [cs.AI] (or arXiv:2609.16795v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2609.16795 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Zhenbin Wang [view email] [v1] Tue, 15 Sep 2026 08:02:52 UTC (11,292 KB) Full-text links: Access Paper: View a PDF of the paper titled Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models, by Zhenbin Wang and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI new | recent | 2026-09 Change to browse by: cs 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?)