# Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression

arXiv: https://arxiv.org/abs/2505.16411 · HTML: https://mlsanity.com/paper/2505.16411/

## Key facts

- Cited by 21 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 26 of its 33 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs](https://mlsanity.com/paper/2407.21771/) (2024)
- [HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding](https://mlsanity.com/paper/2403.00425/) (2024)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination](https://mlsanity.com/paper/2410.04514/) (2024)
- [MoH: Multi-Head Attention as Mixture-of-Head Attention](https://mlsanity.com/paper/2410.11842/) (2024)
- [Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance](https://mlsanity.com/paper/2411.14279/) (2024)
- [ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization](https://mlsanity.com/paper/2406.05981/) (2024)
- [ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2411.15268/) (2024)
- [CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing](https://mlsanity.com/paper/2502.01976/) (2025)
- [LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression](https://mlsanity.com/paper/2503.04982/) (2025)

## Built on by (most cited first, 21 of 21)

- [When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models](https://mlsanity.com/paper/2507.13868/) (2025)
- [Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization](https://mlsanity.com/paper/2509.07864/) (2025)
- ["It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models](https://mlsanity.com/paper/2511.08917/) (2025)
- [When to Think and When to Look: Uncertainty-Guided Lookback](https://mlsanity.com/paper/2511.15613/) (2025)
- [VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering](https://mlsanity.com/paper/2512.12089/) (2025)
- [Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating](https://mlsanity.com/paper/2605.24024/) (2026)
- [ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs](https://mlsanity.com/paper/2606.31054/) (2026)
- [SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering](https://mlsanity.com/paper/2607.04163/) (2026)
- [MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing](https://mlsanity.com/paper/2508.01653/) (2025)
- [PAS : Prelim Attention Score for Detecting Object Hallucinations in Large Vision--Language Models](https://mlsanity.com/paper/2511.11502/) (2025)
- [When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs](https://mlsanity.com/paper/2602.00344/) (2026)
- [Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs](https://mlsanity.com/paper/2603.25711/) (2026)
- [GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models](https://mlsanity.com/paper/2605.01733/) (2026)
- [Targeting the Attention Heads Behind Object Hallucination in LLaVA](https://mlsanity.com/paper/2608.24966/) (2026)
- [Conscious Gaze: Adaptive Attention Mechanisms for Hallucination Mitigation in Vision-Language Models](https://mlsanity.com/paper/2512.05546/) (2025)
- [System-Mediated Attention Imbalances Make Vision-Language Models Say Yes](https://mlsanity.com/paper/2601.12430/) (2026)
- [Logit Lens Supervision for Patch-Level Explanations in Vision-Language Models](https://mlsanity.com/paper/2602.01530/) (2026)
- [Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration](https://mlsanity.com/paper/2605.24957/) (2026)
- [Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering](https://mlsanity.com/paper/2605.29881/) (2026)
- [Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization](https://mlsanity.com/paper/2605.31312/) (2026)
- [Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs](https://mlsanity.com/paper/2607.29412/) (2026)

## Abstract (arXiv)

Despite their remarkable progress in multimodal understanding tasks, large vision language models (LVLMs) often suffer from "hallucinations", generating texts misaligned with the visual context. Existing methods aimed at reducing hallucinations through inference time intervention incur a significant increase in latency. To mitigate this, we present SPIN, a task-agnostic attention-guided head suppression strategy that can be seamlessly integrated during inference, without incurring any significant compute or latency overhead. We investigate whether hallucination in LVLMs can be linked to specific model components. Our analysis suggests that hallucinations can be attributed to a dynamic subset of attention heads in each layer. Leveraging this insight, for each text query token, we selectively suppress attention heads that exhibit low attention to image tokens, keeping the top-K attention heads intact. Extensive evaluations on visual question answering and image description tasks demonstrate the efficacy of SPIN in reducing hallucination scores up to 2.7x while maintaining F1, and improving throughput by 1.8x compared to existing alternatives. Code is available at https://github.com/YUECHE77/SPIN.