# VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck

arXiv: https://arxiv.org/abs/2601.05547 · HTML: https://mlsanity.com/paper/2601.05547/

## Key facts

- Cited by 8 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 21 of its 35 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (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)
- [Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs](https://mlsanity.com/paper/2407.21771/) (2024)
- [Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens](https://mlsanity.com/paper/2411.16724/) (2024)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding](https://mlsanity.com/paper/2402.18476/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Graph Structure Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2112.08903/) (2021)
- [Variational Information Bottleneck for Effective Low-Resource Fine-Tuning](https://mlsanity.com/paper/2106.05469/) (2021)
- [Specializing Word Embeddings (for Parsing) by Information Bottleneck](https://mlsanity.com/paper/1910.00163/) (2019)
- [Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks](https://mlsanity.com/paper/2402.08360/) (2024)
- [Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence](https://mlsanity.com/paper/2412.13949/) (2024)
- [MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification](https://mlsanity.com/paper/2405.19186/) (2024)
- [Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context](https://mlsanity.com/paper/2510.20229/) (2025)

## Built on by (most cited first, 8 of 8)

- [Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs](https://mlsanity.com/paper/2603.25711/) (2026)
- [Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation](https://mlsanity.com/paper/2605.25377/) (2026)
- [IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal](https://mlsanity.com/paper/2606.09347/) (2026)
- [Information-Regularized Attention for Visual-Centric Reasoning](https://mlsanity.com/paper/2607.00434/) (2026)
- [When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoning](https://mlsanity.com/paper/2607.11173/) (2026)
- [The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning](https://mlsanity.com/paper/2607.11436/) (2026)
- [Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers](https://mlsanity.com/paper/2607.27667/) (2026)
- [Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs](https://mlsanity.com/paper/2607.29412/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying visual content. Existing hallucination detection methods primarily rely on output logits or external verification tools, often overlooking their internal mechanisms. In this work, we investigate the outputs of internal attention heads, postulating that specific heads carry the primary signals for truthful generation.However, directly probing these high-dimensional states is challenging due to the entanglement of visual-linguistic syntax and noise. To address this, we propose VIB-Probe, a novel hallucination detection and mitigation framework leveraging the Variational Information Bottleneck (VIB) theory. Our method extracts discriminative patterns across layers and heads while filtering out semantic nuisances through the information bottleneck principle. Furthermore, by leveraging the gradients of our VIB probe, we identify attention heads with strong causal influence on hallucinations and introduce an inference-time intervention strategy for hallucination mitigation. Extensive experiments across diverse benchmarks demonstrate that VIB-Probe significantly outperforms existing baselines in both settings. Our code will be made publicly available.