# Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization arXiv: https://arxiv.org/abs/2411.10436 ยท HTML: https://mlsanity.com/paper/2411.10436/ ## Key facts - Cited by 20 papers in the map (data through 14 Oct 2026). - Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. - Builds on 27 of its 41 references that are in the map. - First posted on arXiv 15 Nov 2024. ## Placed in - Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/) - LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/) ## Builds on (most cited first, 27 of 27) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024) - [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023) - [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023) - [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023) - [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023) - [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023) - [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023) - [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023) - [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023) - [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023) - [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023) - [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023) - [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023) - [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024) - [HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding](https://mlsanity.com/paper/2403.00425/) (2024) - [Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders](https://mlsanity.com/paper/2408.15998/) (2024) - [Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision](https://mlsanity.com/paper/2311.07362/) (2023) - [Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models](https://mlsanity.com/paper/2408.02032/) (2024) - [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024) - [MoVA: Adapting Mixture of Vision Experts to Multimodal Context](https://mlsanity.com/paper/2404.13046/) (2024) - [Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization](https://mlsanity.com/paper/2403.08730/) (2024) - [VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment](https://mlsanity.com/paper/2410.09421/) (2024) - [CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs](https://mlsanity.com/paper/2408.10433/) (2024) - [PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset](https://mlsanity.com/paper/2403.11116/) (2024) - [Self-Supervised Visual Preference Alignment](https://mlsanity.com/paper/2404.10501/) (2024) - [PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions](https://mlsanity.com/paper/2409.05076/) (2024) ## Built on by (most cited first, 20 of 20) - [Grounded Chain-of-Thought for Multimodal Large Language Models](https://mlsanity.com/paper/2503.12799/) (2025) - [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025) - [Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization](https://mlsanity.com/paper/2502.13146/) (2025) - [Aligning Multimodal LLM with Human Preference: A Survey](https://mlsanity.com/paper/2503.14504/) (2025) - [NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2505.20001/) (2025) - [MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization](https://mlsanity.com/paper/2603.03192/) (2026) - [Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance](https://mlsanity.com/paper/2602.01047/) (2026) - [RL makes MLLMs see better than SFT](https://mlsanity.com/paper/2510.16333/) (2025) - [Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model](https://mlsanity.com/paper/2505.24007/) (2025) - [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025) - [Linking Perception, Confidence and Accuracy in MLLMs](https://mlsanity.com/paper/2603.12149/) (2026) - [When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs](https://mlsanity.com/paper/2604.21911/) (2026) - [ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs](https://mlsanity.com/paper/2606.31054/) (2026) - [Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models](https://mlsanity.com/paper/2504.03302/) (2025) - [Human-Data Interaction, Exploration, and Visualization in the AI Era: Challenges and Opportunities](https://mlsanity.com/paper/2603.05542/) (2026) - [Hallucination-aware intermediate representation edit in large vision-language models](https://mlsanity.com/paper/2603.29405/) (2026) - [V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2608.25580/) (2026) - [DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs](https://mlsanity.com/paper/2609.28570/) (2026) - [MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging](https://mlsanity.com/paper/2609.32422/) (2026) - [DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing](https://mlsanity.com/paper/2609.36440/) (2026) ## Abstract (arXiv) Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. Recent works have attempted to apply Direct Preference Optimization (DPO) to enhance the performance of MLLMs, but have shown inconsistent improvements in mitigating hallucinations. To address this issue more effectively, we introduce Hallucination-targeted Direct Preference Optimization (HDPO) to reduce hallucinations in MLLMs. Unlike previous approaches, our method tackles hallucinations from their diverse forms and causes. Specifically, we develop three types of preference pair data targeting the following causes of MLLM hallucinations: (1) insufficient visual capabilities, (2) long context generation, and (3) multimodal conflicts. Experimental results demonstrate that our method achieves superior performance across multiple hallucination evaluation datasets, surpassing most state-of-the-art (SOTA) methods and highlighting the potential of our approach. Ablation studies and in-depth analyses further confirm the effectiveness of our method and suggest the potential for further improvements through scaling up.