Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization
While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are still underexplored. In this paper, we experimentally analyze the hallucination cause and propose C3PO, a training-based mitigation framework comprising \textbf{C}hain-of-Thought \textbf{C}ompression and \textbf{C}ontrastive \textbf{P}reference \textbf{O}ptimization. Firstly, we identify that introducing reasoning mechanisms exacerbates models' reliance on language priors while overlooking visual inputs, which can produce CoTs with reduced visual cues but redundant text tokens. To this end, we propose to selectively filter redundant thinking tokens for a more compact and signal-efficient CoT representation that preserves task-relevant information while suppressing noise. In addition, we observe that the quality of the reasoning trace largely determines whether hallucination emerges in subsequent responses. To leverage this insight, we introduce a reasoning-enhanced preference tuning scheme that constructs training pairs using high-quality AI feedback. We further design a multimodal hallucination-inducing mechanism that elicits models' inherent hallucination patterns via carefully crafted inducers, yielding informative negative signals for contrastive correction. We provide theoretical justification for the effectiveness and demonstrate consistent hallucination reduction across diverse MLRMs and benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningSimilar Papers 제목 키워드 기반
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability oft…
DiagnosticHallucinationMathMultimodal Reasoning+1ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding
While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in open-ended visual question answering, they remain vulnerable to hallucinations. These are outputs that contradict or misrepresent input …
HallucinationQuestion AnsweringVisual Question AnsweringSeeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
Multimodal large language models (MLLMs) suffer from pronounced hallucinations in remote sensing visual question-answering (RS-VQA), primarily caused by visual grounding failures in large-scale scenes or misinterpretatio…
Visual GroundingReasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based metho…
Multimodal ReasoningAnswer GenerationThinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of tho…
HallucinationMultimodal Reasoning