Copertina

Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fang, Hao, Li, Jinyu, Kong, Jiawei, Zhuang, Tianqu, Gao, Kuofeng, Chen, Bin, Xia, Shu-Tao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
di: Kong, Jiawei, et al.
Pubblicazione: (2026)

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
di: Fang, Hao, et al.
Pubblicazione: (2025)

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
di: Fang, Hao, et al.
Pubblicazione: (2025)

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective
di: Fang, Hao, et al.
Pubblicazione: (2026)

Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
di: Yang, Xiaochen, et al.
Pubblicazione: (2026)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
di: Ma, Xinyin, et al.
Pubblicazione: (2025)

Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
di: Liu, Wenqi, et al.
Pubblicazione: (2025)

Generating Effective CoT Traces for Mitigating Causal Hallucination
di: Zhao, Yiheng, et al.
Pubblicazione: (2026)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
di: Mondal, Debjyoti, et al.
Pubblicazione: (2024)

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
di: Kong, Jiawei, et al.
Pubblicazione: (2025)

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
di: Fang, Hao, et al.
Pubblicazione: (2025)

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP
di: Kong, Jiawei, et al.
Pubblicazione: (2025)

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
di: Tong, Bingkui, et al.
Pubblicazione: (2025)

CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning
di: Fang, Yuanheng, et al.
Pubblicazione: (2025)

Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
di: Wang, Yizhi, et al.
Pubblicazione: (2026)

Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing
di: Chen, Bin, et al.
Pubblicazione: (2024)

Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
di: Yu, Hongyao, et al.
Pubblicazione: (2024)

JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework
di: Zhou, Yuxuan, et al.
Pubblicazione: (2025)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
di: Lim, Byeonggeuk, et al.
Pubblicazione: (2026)

ICAS: Detecting Training Data from Autoregressive Image Generative Models
di: Yu, Hongyao, et al.
Pubblicazione: (2025)

AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
di: Li, Xiping, et al.
Pubblicazione: (2025)

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
di: Compagnoni, Alberto, et al.
Pubblicazione: (2025)

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
di: Fang, Hao, et al.
Pubblicazione: (2024)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
di: Fu, Yuhan, et al.
Pubblicazione: (2024)

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
di: Qiu, Yixiang, et al.
Pubblicazione: (2024)

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework
di: Tiwari, Nitya, et al.
Pubblicazione: (2025)

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
di: Jiang, Dongzhi, et al.
Pubblicazione: (2025)

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
di: Feng, Kehua, et al.
Pubblicazione: (2025)

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
di: Tong, Zhao, et al.
Pubblicazione: (2026)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
di: Sprague, Zayne, et al.
Pubblicazione: (2024)

V2T-CoT: From Vision to Text Chain-of-Thought for Medical Reasoning and Diagnosis
di: Wang, Yuan, et al.
Pubblicazione: (2025)

Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding
di: Kong, Zhifeng, et al.
Pubblicazione: (2025)

CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
di: Bi, Ziqian, et al.
Pubblicazione: (2025)

Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning
di: Yoo, Seunghyun
Pubblicazione: (2025)

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
di: Dong, Zhuobai, et al.
Pubblicazione: (2025)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
di: Wan, Faxian, et al.
Pubblicazione: (2026)

Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation
di: Luo, Yijia, et al.
Pubblicazione: (2025)

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
di: He, Zhentao, et al.
Pubblicazione: (2025)

Investigating CoT Monitorability in Large Reasoning Models
di: Yang, Shu, et al.
Pubblicazione: (2025)