mlsanityData to 7 Oct 2026

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization

arXiv 2411.10436 ↗First posted 15 Nov 2024cs.CL cs.AI cs.CVcited by 20

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

also in 1 more
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.

Key facts. Cited by 20 papers in the map (data through 7 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.

Builds on

27 of 41 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs19 Aug
  2. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models4 Aug
  3. 2024PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset17 Mar
  4. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding1 Mar
  5. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback1 Dec
  6. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  7. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  8. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization28 Nov
  9. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation13 Nov
  10. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision13 Nov
  11. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  5. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  6. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  7. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  8. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  9. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 197
  10. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  11. 2024Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencentcited by 89
  12. 2024MoVA: Adapting Mixture of Vision Experts to Multimodal Contextcited by 82
4 more
  1. 2024Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimizationcited by 75
  2. 2024VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignmentcited by 56
  3. 2024Self-Supervised Visual Preference Alignmentcited by 31
  4. 2024PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questionscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 11.

20 papers.

Sort:

By area:

  1. 2025Grounded Chain-of-Thought for Multimodal Large Language Modelscited by 57
  2. 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMscited by 30
  3. 2025Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationcited by 29
  4. 2025Aligning Multimodal LLM with Human Preference: A Surveycited by 12
  5. 2025NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identificationcited by 5
  6. 2026Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidancecited by 5
  7. 2025RL makes MLLMs see better than SFTcited by 3
  8. 2026MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimizationcited by 3
  9. 2025Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Modelcited by 2
  10. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  11. 2026Linking Perception, Confidence and Accuracy in MLLMscited by 2
  12. 2026When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMscited by 2
8 more
  1. 2026ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMscited by 2
  2. 2025Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Modelscited by 1
  3. 2026Human-Data Interaction, Exploration, and Visualization in the AI Era: Challenges and Opportunitiescited by 0
  4. 2026Hallucination-aware intermediate representation edit in large vision-language modelscited by 0
  5. 2026V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learningcited by 0
  6. 2026DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMscited by 0
  7. 2026MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Mergingcited by 0
  8. 2026DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
  2. 2025TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
  3. 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
  4. 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
  5. 2026Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization
  6. 2026DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations
  7. 2026Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language Models
  8. 2025Stop learning it all to mitigate visual hallucination, Focus on the hallucination target