# MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games Source: [MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games]() Collection index: [llms.txt]() Data updated: 2026-04-16T05:00:11.996Z Authors: Shufang Lin, Muyang Chen, Xiabing Zhou, Rongrong Zhang, Dayou Zhang, Fangxin Wang Published: 2026-04-14T13:07:54.000Z ## Abstract Understanding human intent in complex multi-turn interactions remains a fundamental challenge in human-computer interaction and behavioral analysis. While existing intent recognition datasets focus mainly on single utterances or simple dialogues, real-world scenarios often involve sophisticated strategic interactions where participants must maintain complex deceptive narratives over extended periods. To address this gap, we introduce MISID, a comprehensive multimodal, multi-turn, and multi-participant benchmark for intent recognition. Sourced from high-stakes social strategy games, MISID features a fine-grained, two-tier multi-dimensional annotation scheme tailored for long-context discourse analysis and evidence-based causal tracking. Our systematic evaluation of state-of-the-art Multimodal Large Language Models (MLLMs) on MISID reveals critical deficiencies in complex scenarios, including text-prior visual hallucination, impaired cross-modal synergy, and limited capacity in chaining causal cues. Consequently, we propose FRACTAM as a baseline framework. Using a \`\`Decouple-Anchor-Reason'' paradigm, FRACTAM reduces text bias by extracting pure unimodal factual representations, employs two-stage retrieval for long-range factual anchoring, and constructs explicit cross-modal evidence chains. Extensive experiments demonstrate that FRACTAM enhances mainstream models' performance in complex strategic tasks, improving hidden intent detection and inference while maintaining robust perceptual accuracy. Our dataset is available at https://naislab.cn/datasets/MISID. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Emotion Analysis on MISID](): Emotion Analysis; MISID; Emotion State Accuracy: 90.75. - [Hidden Intent Inference on MISID](): Hidden Intent Inference; MISID; Hidden Intent Inference Score: 53.27. - [Identity Judgment on MISID](): Identity Judgment; MISID; Identity Judgment Accuracy: 72.22. - [Lie Detection on MISID](): Lie Detection; MISID; Lie Detection Accuracy: 61.54. - [Subjectivity Analysis on MISID](): Subjectivity Analysis; MISID; Subjectivity Accuracy: 94.85. ## Original sources and implementation [Original paper]() [PDF]()