Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes

[2601.07737] Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2601.07737 (cs) [Submitted on 12 Jan 2026 ( v1 ), last revised 25 Aug 2026 (this version, v3)] Title: Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes Authors: Chen Ling , Tongwei Zhang , Hanqian Li , Nai Ding View PDF HTML (experimental) Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in mainstream visual understanding tasks, but their ability to process action scenes that contradict everyday common sense remains undertested. To address this gap, we introduce CAIT, a benchmark comprising 400 high-fidelity synthetic scenes focused on counter-intuitive visual actions, such as ``a rabbit is chasing a tiger'', where visual evidence explicitly contradicts common-sense expectations. We evaluate human, leading proprietary models (e.g., Claude and Gemini), and 14 representative open-source MLLMs. Humans achieve near-perfect performance (around 0.95 accuracy) and proprietary models demonstrate robust understanding (achieving up to 0.88 accuracy), standard open-source instruction-tuned models perform at the chance level. Further analysis demonstrates that this failure is driven by a strong language prior: rather than trusting the visual input, they automatically override the anomalous visual signals with statistically common text descriptions. Although introducing Chain-of-Thought reasoning mechanisms can improve accuracy, it significantly slows down the response and generates a new failure mode: models overthink the scenario and refuse to accept the actual visual content simply because it violates real-world physical laws. Finally, we demonstrate that targeted fine-tuning and structured prompting can effectively mitigate this reliance on language priors, enabling open-source models to accurately ground their reasoning in actual visual evidence. Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2601.07737 [cs.CV] (or arXiv:2601.07737v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2601.07737 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chen Ling [ view email ] [v1] Mon, 12 Jan 2026 17:15:45 UTC (8,806 KB) [v2] Tue, 26 May 2026 12:27:32 UTC (11,555 KB) [v3] Tue, 25 Aug 2026 07:21:53 UTC (11,555 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-01 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation 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

• Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes#670460
• Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?#821879
• Feeling iffy about generative AI: Investigating Audiences’ Trustworthiness Perceptions of Task-Specific AI disclosures#327808
• Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure#1117767
• MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models#1145087