mlsanityData to 7 Oct 2026

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

arXiv 2311.16839 ↗First posted 28 Nov 2023cs.CV cs.CLcited by 223

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

also in 1 more
Abstract (arXiv)

Multimodal large language models have made significant advancements in recent years, yet they still suffer from a common issue known as the "hallucination problem", in which the models generate textual descriptions that inaccurately depict or entirely fabricate content from associated images. This paper introduces a novel solution, Hallucination-Aware Direct Preference Optimization (HA-DPO), which reframes the hallucination problem as a preference selection task. The model is trained to favor the non-hallucinating response when presented with two responses of the same image (one accurate and one hallucinatory). Furthermore, this paper proposes an efficient pipeline for constructing positive~(non-hallucinatory) and negative~(hallucinatory) sample pairs, ensuring a high-quality, style-consistent dataset for robust preference learning. When applied to three mainstream multimodal models, HA-DPO significantly reduced hallucination issues and amplified the models' generalization capabilities. Notably, the MiniGPT-4 model, when enhanced with HA-DPO, demonstrated a substantial improvement: POPE accuracy rose from 51.13% to 86.13% (an absolute improvement of 35%), and the MME score surged from 932.00 to 1326.46 (a relative improvement of 42.32%). The codes, models, and datasets are made accessible at https://opendatalab.github.io/HA-DPO.

Key facts. Cited by 223 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 38 of its 41 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

38 of 41 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  2. 2023Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models9 Oct
  3. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  4. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Models29 Aug
  5. 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug
  6. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2023Visual Instruction Tuningcited by 7,792
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  10. 2017Deep reinforcement learning from human preferencescited by 3,846
  11. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  12. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
20 more
  1. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  2. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  6. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  7. 2023LIMA: Less Is More for Alignmentcited by 1,080
  8. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  9. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  10. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  11. 2018Object Hallucination in Image Captioningcited by 661
  12. 2023Textbooks Are All You Needcited by 561
  13. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  14. 2017Deep Reinforcement Learning: An Overviewcited by 327
  15. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  16. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 168
  17. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 155
  18. 2017Deep Exploration via Randomized Value Functionscited by 155
  19. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  20. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 78; 2025: 92; 2026: 52.

223 papers.

Sort:

By area:

  1. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
  2. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 468
  3. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  4. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  5. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  6. 2024From r to Q^*: Your Language Model is Secretly a Q-Functioncited by 242
  7. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 197
  8. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  9. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 194
  10. 2024Direct Preference Optimization of Video Large Multimodal Models from Language Model Rewardcited by 145
  11. 2024RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthinesscited by 129
  12. 2024IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decodingcited by 118
38 more
  1. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 98
  2. 2024Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequencescited by 93
  3. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 93
  4. 2024mDPO: Conditional Preference Optimization for Multimodal Large Language Modelscited by 92
  5. 2024Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Modelscited by 90
  6. 2024Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedbackcited by 80
  7. 2024Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvementcited by 74
  8. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Modelcited by 73
  9. 2024V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimizationcited by 67
  10. 2024Vision-Language Models Can Self-Improve Reasoning via Reflectioncited by 66
  11. 2024VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understandingcited by 65
  12. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  13. 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Keycited by 64
  14. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  15. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  16. 2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuningcited by 61
  17. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Modelscited by 57
  18. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
  19. 2024VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignmentcited by 56
  20. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steeringcited by 56
  21. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  22. 2024CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMscited by 49
  23. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  24. 2024Offline Regularised Reinforcement Learning for Large Language Models Alignmentcited by 48
  25. 2024Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Modelscited by 46
  26. 2024Probing Visual Language Priors in VLMscited by 44
  27. 2024LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillationcited by 43
  28. 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decodingcited by 42
  29. 2024CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Modelscited by 37
  30. 2024Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimizationcited by 34
  31. 2024MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Modelscited by 34
  32. 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resamplingcited by 32
  33. 2024Self-Supervised Visual Preference Alignmentcited by 31
  34. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  35. 2025Temporal Preference Optimization for Long-Form Video Understandingcited by 28
  36. 2025Mitigating Object Hallucinations via Sentence-Level Early Interventioncited by 28
  37. 2024CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenariocited by 27
  38. 2024Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Modelscited by 27

50 most cited of 223 All 223 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
  2. 2025TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
  3. 2026Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language Models
  4. 2026Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization
  5. 2025Stop learning it all to mitigate visual hallucination, Focus on the hallucination target
  6. 2026Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning
  7. 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
  8. 2024Automated Multi-level Preference for MLLMs