Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation

[2608.14655] Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14655 (cs) [Submitted on 31 Jul 2026] Title: Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation Authors: Hongbo Jiang , Jie Li , Yunhang Shen , Tianyu Xie , Pingyang Dai View a PDF of the paper titled Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation, by Hongbo Jiang and 4 other authors View PDF HTML (experimental) Abstract: Omni-Large Language Models (Omni-LLMs) power complex multi-modal reasoning in applications like World Action Models and autonomous agents. However, their strong performance often masks a profound Perceptual-Decision Misalignment (PDM), where decisions remain unfaithful to multi-modal perceptions. To diagnose this, we formalize Causal Modality Sensitivity (CMS), operationalized via a dual-lens framework: Answer Retention Rate (ARR) at the macro behavioral level, and Logit Angular Discrepancy (LAD) to track microscopic distribution shifts. We also curate CausalMSBench, a diagnostic dataset isolating language priors. Benchmarking reveals that popular Omni-LLMs exhibit critically low CMS, showing negligible distribution shifts even when key modalities are removed. To rectify this, we propose Modality Subspace Activation (MSA), a training-free inference-time framework that uses Singular Value Decomposition (SVD) to estimate modal activation strengths. MSA dynamically balances modal projections in the last hidden state, effectively restoring CMS across benchmarks. Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.14655 [cs.LG] (or arXiv:2608.14655v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14655 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hongbo Jiang [ view email ] [v1] Fri, 31 Jul 2026 05:46:40 UTC (417 KB) Full-text links: Access Paper: View a PDF of the paper titled Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation, by Hongbo Jiang and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CV 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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

• ENWAR: A RAG-Empowered Multi-Modal LLM Framework for Wireless Environment Perception#334296
• The Decision Value of Perception Compute#1130752
• Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs#180691
• Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs#673611
• Which Consciousness Can Be Artificialized? Local Percept-Perceiver Phenomenon for the Existence of Machine Consciousness#171187