{"ID":5438657,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T06:11:10.270297527Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31187","arxiv_id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","abstract":"Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks. Yet their ability to deny an action by recognizing when an activity is not happening despite strong contextual cues remains largely unexplored. We introduce UCF101-AD, a large-scale benchmark consisting of paired Action-Presence and Action-Denial clips, designed to evaluate this capacity for denial. Each negative video in UCF101-AD preserves the same contextual and motion cues, including persons, objects, and locations, as its positive counterpart, but the defining action itself is explicitly absent. Evaluating 20 state-of-the-art MLLMs reveals a consistent failure: models that exceed 85% accuracy on the positive action classes collapse below 50% on their action-denial counterparts, indicating a strong inclination to affirm plausible actions rather than verify that they truly occur. This exposes a critical blind spot in modern video understanding: the inability to reason causally about whether a motion actually happens. To probe this issue, we explore a causal graph formulation, CausalAct, which expresses scene structure through natural-language prompts linking context, interaction, and motion. Incorporating such causal cues substantially reduces false positives, demonstrating that denial is a learnable reasoning skill. UCF101-AD provides a new lens for diagnosing and improving causal reasoning in multimodal models. Dataset and relevant code: https://github.com/raiyaan-abdullah/Learn-to-Deny.","short_abstract":"Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks. Yet their ability to deny an action by recognizing when an activity is not happening despite strong contextual cues remains largely unexplored. We introduce...","url_abs":"https://arxiv.org/abs/2606.31187","url_pdf":"https://arxiv.org/pdf/2606.31187v1","authors":"[\"Raiyaan Abdullah\",\"Shehreen Azad\",\"Yogesh Singh Rawat\"]","published":"2026-06-30T06:16:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":613772,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-01T01:17:58.482524686Z","DeletedAt":null,"paper_id":5438657,"paper_url":"https://arxiv.org/abs/2606.31187","paper_title":"Learning to Deny: Action Denial in Multimodal Large Language Models","repo_url":"https://github.com/raiyaan-abdullah/Learn-to-Deny","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}