# Hallucination mitigation in LVLMs

Area: [Multimodal LLMs / vision-language models](https://mlsanity.com/mllm/index.md). HTML: https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/

## Key facts

- Hallucination mitigation in LVLMs: 599 papers on arXiv since 2022 (data through 14 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).
- 15 new papers 17 Sep–14 Oct.

## Most cited here

- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023), cited by 204 papers here
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023), cited by 187 papers here
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023), cited by 164 papers here
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023), cited by 142 papers here
- [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023), cited by 99 papers here
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023), cited by 97 papers here
- [Woodpecker: Hallucination Correction for Multimodal Large Language Models](https://mlsanity.com/paper/2310.16045/) (2023), cited by 83 papers here
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023), cited by 82 papers here
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024), cited by 77 papers here
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024), cited by 76 papers here

## New (17 Sep–14 Oct)

- [Hallucination-aware Faithful Reasoning in Remote Sensing](https://mlsanity.com/paper/2610.18369/) (2026-10-13)
- [From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models](https://mlsanity.com/paper/2610.17706/) (2026-10-13)
- [Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning](https://mlsanity.com/paper/2610.14976/) (2026-10-10)
- [PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2610.14635/) (2026-10-10)
- [Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations](https://mlsanity.com/paper/2610.11907/) (2026-10-08)
- [From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment](https://mlsanity.com/paper/2610.11826/) (2026-10-08)
- [Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models](https://mlsanity.com/paper/2610.09496/) (2026-10-07)
- [ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs](https://mlsanity.com/paper/2610.06056/) (2026-10-05)
- [Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting](https://mlsanity.com/paper/2609.38979/) (2026-10-01)
- [Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery](https://mlsanity.com/paper/2609.37263/) (2026-09-29)
- [DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing](https://mlsanity.com/paper/2609.36440/) (2026-09-29)
- [Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models](https://mlsanity.com/paper/2609.35294/) (2026-09-28)
- [Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models](https://mlsanity.com/paper/2609.29048/) (2026-09-24)
- [DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs](https://mlsanity.com/paper/2609.28570/) (2026-09-23)
- [SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models](https://mlsanity.com/paper/2609.24198/) (2026-09-21)