# Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning

arXiv: https://arxiv.org/abs/2403.10492 · HTML: https://mlsanity.com/paper/2403.10492/

## Key facts

- Cited by 7 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 32 of its 59 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)
- [IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning](https://mlsanity.com/paper/2110.13214/) (2021)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2306.09265/) (2023)
- [Grounding Language Models to Images for Multimodal Inputs and Outputs](https://mlsanity.com/paper/2301.13823/) (2023)
- [HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data](https://mlsanity.com/paper/2311.13614/) (2023)
- [Hallucination Augmented Contrastive Learning for Multimodal Large Language Model](https://mlsanity.com/paper/2312.06968/) (2023)
- [CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment](https://mlsanity.com/paper/2203.07190/) (2022)
- [Black Box Adversarial Prompting for Foundation Models](https://mlsanity.com/paper/2302.04237/) (2023)
- [How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts](https://mlsanity.com/paper/2402.13220/) (2024)

## Built on by (most cited first, 7 of 7)

- [Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs](https://mlsanity.com/paper/2411.09968/) (2024)
- [Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning](https://mlsanity.com/paper/2408.17150/) (2024)
- [Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment](https://mlsanity.com/paper/2512.04356/) (2025)
- [Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning](https://mlsanity.com/paper/2603.00511/) (2026)
- [SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation](https://mlsanity.com/paper/2603.27898/) (2026)
- [Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation](https://mlsanity.com/paper/2605.25377/) (2026)
- [When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models](https://mlsanity.com/paper/2608.19208/) (2026)

## Abstract (arXiv)

Mitigating hallucinations of Large Vision Language Models,(LVLMs) is crucial to enhance their reliability for general-purpose assistants. This paper shows that such hallucinations of LVLMs can be significantly exacerbated by preceding user-system dialogues. To precisely measure this, we first present an evaluation benchmark by extending popular multi-modal benchmark datasets with prepended hallucinatory dialogues powered by our novel Adversarial Question Generator (AQG), which can automatically generate image-related yet adversarial dialogues by adopting adversarial attacks on LVLMs. On our benchmark, the zero-shot performance of state-of-the-art LVLMs drops significantly for both the VQA and Captioning tasks. Next, we further reveal this hallucination is mainly due to the prediction bias toward preceding dialogues rather than visual content. To reduce this bias, we propose Adversarial Instruction Tuning (AIT) that robustly fine-tunes LVLMs against hallucinatory dialogues. Extensive experiments show our proposed approach successfully reduces dialogue hallucination while maintaining performance.