Awesome Multimodal Large Language Models Hallucination Mitigation

This is a list of some awesome works on mitigating hallucination in large multimodal models.

📚Survey

1. Hallucination of Multimodal Large Language Models: A Survey (Apr. 30, 2024)
2. A Survey on Hallucination in Large Vision-Language Models (Feb. 1, 2024)

📊Benchmarks

1. Object Hallucination in Image Captioning(Sep. 6, 2018, EMNLP 2018)
2. Evaluating Object Hallucination in Large Vision-Language Models (May. 17, 2023, EMNLP 2023)
3. Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs (Jan. 11, 2024, CVPR 2024)
4. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models (Jun. 23, 2023)
5. MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations (Mar. 20, 2025, CVPR 2025)
6. AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation (Nov. 13, 2023)
7. Aligning Large Multimodal Models with Factually Augmented RLHF (Sep. 25, 2023, ACL 2024)

👏Hallucination Mitigation

1. MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations (Mar. 20, 2025, CVPR 2025)
2. ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models (Mar. 17, 2025)
3. Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding (Mar. 13, 2025)
4. EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens (Mar. 10, 2025)
5. Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs (Mar. 4, 2025, ICLR 2025)
6. PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training (Mar. 9, 2025, ICLR 2025)
7. Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding (Mar. 1, 2025, CVPR 2025)
8. Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models (Feb. 24, 2025)
9. Refine Knowledge of Large Language Models via Adaptive Contrastive Learning (Feb. 11, 2025, ICLR 2025)
10. Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key (Jan. 16, 2025, CVPR 2025)
11. VASparse: Towards Efficient Visual Hallucination Mitigation for Large Vision-Language Model via Visual-Aware Sparsification (Jan. 11, 2025, CVPR 2025)
12. Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection (Dec. 18, 2024, CVPR 2025)
13. Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations (Oct. 3, 2024, ICLR 2025)
14. Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens (Nov. 23, 2024, CVPR 2025)
15. ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models (Nov. 22, 2024, CVPR 2025)
16. Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders (Aug. 28, 2024, ICLR 2025)
17. Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models (Aug. 4, 2024, ICLR 2025)
18. Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs (Jul. 31, 2024, ECCV 2024)
19. Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention (Jun. 18, 2024, CVPR 2025)
20. Reducing Hallucinations in Vision-Language Models via Latent Space Steering (Oct. 21, 2024, ICLR 2025)
21. Woodpecker: Hallucination Correction for Multimodal Large Language Models (Oct. 10, 2024)
22. Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization (May. 24, 2024, NeurIPS 2024)
23. Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding (Mar. 27, 2024, ACL 2024)
24. Mitigating Object Hallucination via Concentric Causal Attention (Oct. 21, 2024, NeurIPS 2024)
25. DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination (Oct. 6, 2024 EMNLP 2024)
26. Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models (Feb. 2, 2024, ICLR 2024)
27. Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs (Jan. 11, 2024, CVPR 2024)
28. Hallucination Augmented Contrastive Learning for Multimodal Large Language Model (Dec. 12, 2023, CVPR 2024)
29. OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation (Nov. 29, 2023, CVPR 2024)
30. Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding (Nov. 28, 2023, CVPR 2024)
31. Analyzing and Mitigating Object Hallucination in Large Vision-Language Models (Oct. 1, 2023, ICLR 2024)
32. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models (Sep. 7, 2023, ICLR 2024)
33. Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Jun. 26, 2023, NeurIPS 2023)

⭐Acknowledgment

This project is inspired by Awesome-MLLM-Hallucination and Awesome-Multimodal-Large-Language-Models. Thanks for their contribution to the research community.