mlsanityData to 14 Oct 2026

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback

arXiv 2404.14233 ↗First posted 22 Apr 2024cs.CV cs.AI cs.CLcited by 80

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

also in 1 more
Abstract (arXiv)

The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts, significantly restricting the usages of LVLMs. Most previous work detects and mitigates hallucination at the coarse-grained level or requires expensive annotation (e.g., labeling by proprietary models or human experts). To address these issues, we propose detecting and mitigating hallucinations in LVLMs via fine-grained AI feedback. The basic idea is that we generate a small-size sentence-level hallucination annotation dataset by proprietary models, whereby we train a hallucination detection model which can perform sentence-level hallucination detection, covering primary hallucination types (i.e., object, attribute, and relationship). Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model. Furthermore, we propose differentiating the severity of hallucinations, and introducing a Hallucination Severity-Aware Direct Preference Optimization (HSA-DPO) for mitigating hallucination in LVLMs by incorporating the severity of hallucinations into preference learning. Extensive experiments demonstrate the effectiveness of our method.

Key facts. Cited by 80 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 16 of its 31 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

16 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback1 Dec
  2. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization28 Nov

Other references · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  9. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  10. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  11. 2018Object Hallucination in Image Captioningcited by 669
  12. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
2 more
  1. 2023Silkie: Preference Distillation for Large Visual Language Modelscited by 130
  2. 2023Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistantscited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 34; 2026: 30.

80 papers.

Sort:

By area:

  1. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  2. 2024RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthinesscited by 131
  3. 2024mDPO: Conditional Preference Optimization for Multimodal Large Language Modelscited by 92
  4. 2024Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvementcited by 74
  5. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 73
  6. 2024VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignmentcited by 58
  7. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Modelscited by 57
  8. 2024DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucinationcited by 48
  9. 2024Probing Visual Language Priors in VLMscited by 45
  10. 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decodingcited by 43
  11. 2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoningcited by 33
  12. 2025Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainabilitycited by 28
38 more
  1. 2025Fine-tuning Large Language Models for Improving Factuality in Legal Question Answeringcited by 28
  2. 2025Mitigating Object Hallucinations via Sentence-Level Early Interventioncited by 28
  3. 2024A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applicationscited by 27
  4. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 27
  5. 2024Modality-Fair Preference Optimization for Trustworthy MLLM Alignmentcited by 26
  6. 2025AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMscited by 19
  7. 2024T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Conceptscited by 14
  8. 2025Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimizationcited by 14
  9. 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimizationcited by 14
  10. 2025Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perceptioncited by 10
  11. 2025Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimizationcited by 10
  12. 2025Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMscited by 9
  13. 2025Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attentioncited by 9
  14. 2026Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steeringcited by 8
  15. 2024Systematic Reward Gap Optimization for Mitigating VLM Hallucinationscited by 7
  16. 2024Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigationcited by 7
  17. 2025Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Modelscited by 7
  18. 2025Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilizationcited by 6
  19. 2025Self-Improvement in Multimodal Large Language Models: A Surveycited by 6
  20. 2024DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmarkcited by 5
  21. 2024Extract Free Dense Misalignment from CLIPcited by 5
  22. 2025UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Modelscited by 5
  23. 2025LPOI: Listwise Preference Optimization for Vision Language Modelscited by 5
  24. 2025Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Modelscited by 5
  25. 2025InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaborationcited by 5
  26. 2026KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothingcited by 5
  27. 2026Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppressioncited by 5
  28. 2025Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillationcited by 4
  29. 2025Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMscited by 4
  30. 2025Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigationcited by 4
  31. 2025Transferring Textual Preferences to Vision-Language Understanding through Model Mergingcited by 3
  32. 2025Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflectioncited by 3
  33. 2026Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinationscited by 3
  34. 2026Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbationcited by 3
  35. 2025OViP: Online Vision-Language Preference Learning for VLM Hallucinationcited by 2
  36. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  37. 2026V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answeringcited by 2
  38. 2026Mitigating Multimodal Hallucination via Phase-wise Self-rewardcited by 2

50 most cited of 80 All 80 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
  2. 2026Scalable Token-Level Hallucination Detection in Large Language Models
  3. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering
  4. 2024A Survey on Hallucination in Large Vision-Language Models
  5. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations
  6. 2026Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
  7. 2026HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token
  8. 2025Stop learning it all to mitigate visual hallucination, Focus on the hallucination target