mlsanityData to 7 Oct 2026

Hallucination mitigation in LVLMs

599 papers2 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: hallucination, hallucinations, visual, lvlms, decoding

Key facts. Hallucination mitigation in LVLMs: 599 papers on arXiv since 2022 (data through 7 Oct 2026). 204 of its 599 mapped papers (34%) cite “Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding” (2023, arXiv 2311.16922). 187 of its 599 mapped papers (31%) cite “Evaluating Object Hallucination in Large Vision-Language Models” (2023, arXiv 2305.10355). 9 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

9 new papers, 17 Sep – 7 Oct; 2 this week.

  1. This week · 2
  2. Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
  3. ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs
  4. Earlier · 7
  5. Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting
  6. Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
  7. DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing
  8. Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models
  9. Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models
  10. DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs
  11. SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models

Foundations

Most cited by papers here

  1. Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding2023cited by 204 here
  2. Evaluating Object Hallucination in Large Vision-Language Models2023cited by 187 here
  3. OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation2023cited by 164 here
  4. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning2023cited by 142 here
  5. AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation2023cited by 99 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 55 here
  2. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 143 here
  3. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 187 here
  4. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 109 here
  5. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 142 here
  6. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 82 here
  7. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 97 here
  8. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 204 here
  9. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decodingcited by 77 here
  10. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 60 here
14 more it builds on, not in this chain
  1. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 56 here
  2. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 65 here
  3. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 121 here
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 182 here
  5. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 56 here
  6. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 83 here
  7. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 99 here
  8. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 70 here
  9. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 164 here
  10. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 66 here
  11. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 76 here
  12. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decodingcited by 69 here
  13. 2024Multi-Modal Hallucination Control by Visual Information Groundingcited by 63 here
  14. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMscited by 60 here

The 24 most cited of 1,042.

Browse

30 of 599, ranked 6–35

  1. 6Analyzing and Mitigating Object Hallucination in Large Vision-Language Models202397
  2. 7Woodpecker: Hallucination Correction for Multimodal Large Language Models202383
  3. 8Detecting and Preventing Hallucinations in Large Vision Language Models202382
  4. 9Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding202477
  5. 10A Survey on Hallucination in Large Vision-Language Models202476
  6. 11Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization202370
  7. 12HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding202469
  8. 13RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback202366
  9. 14Multi-Modal Hallucination Control by Visual Information Grounding202463
  10. 15Hallucination of Multimodal Large Language Models: A Survey202460
All 30
  1. 16Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs202460
  2. 17HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models202356
  3. 18HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data202352
  4. 19Hallucination Augmented Contrastive Learning for Multimodal Large Language Model202351
  5. 20IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding202443
  6. 21CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning202337
  7. 22Evaluation and Analysis of Hallucination in Large Vision-Language Models202336
  8. 23Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models202334
  9. 24Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens202432
  10. 25Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision202332
  11. 26Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites202332
  12. 27MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation202430
  13. 28Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models202428
  14. 29DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination202426
  15. 30Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models202425
  16. 31Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective202424
  17. 32Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models202523
  18. 33Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention202421
  19. 34Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization202420
  20. 35Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key202517