# Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models

arXiv: https://arxiv.org/abs/2508.01678 · HTML: https://mlsanity.com/paper/2508.01678/

## Key facts

- Cited by 4 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 19 of its 27 references that are in the map.
- First posted on arXiv 3 Aug 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, 19 of 19)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023)
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2310.05338/) (2023)
- [Fine-grained Image Captioning with CLIP Reward](https://mlsanity.com/paper/2205.13115/) (2022)
- [DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination](https://mlsanity.com/paper/2410.04514/) (2024)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)
- [DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models](https://mlsanity.com/paper/2411.18659/) (2024)
- [The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?](https://mlsanity.com/paper/2504.10020/) (2025)
- [Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning](https://mlsanity.com/paper/2505.03703/) (2025)
- [Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models](https://mlsanity.com/paper/2504.01589/) (2025)

## Built on by (most cited first, 4 of 4)

- [VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft](https://mlsanity.com/paper/2508.18722/) (2025)
- [Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs](https://mlsanity.com/paper/2603.09095/) (2026)
- [Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases](https://mlsanity.com/paper/2604.24972/) (2026)
- [Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models](https://mlsanity.com/paper/2606.19944/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the need for separate text inputs and forces the model to process all content through the visual channel. We evaluate this method on three popular open-source VLMs: Qwen2.5-VL, LLaVA-1.5, and InstructBLIP. The results reveal sharp differences. Prompt-in-Image improves Qwen2.5-VL's performance, increasing POPE accuracy by 4.1 percent (from 80.2 percent to 84.3 percent) and also reducing hallucination rates on MS-COCO. In contrast, LLaVA-1.5 and InstructBLIP experience a severe performance drop, with accuracy falling from around 84 percent to near-random levels. Through detailed analysis, we found that CLIP-based encoders in LLaVA and InstructBLIP exhibit excessive attention bias toward embedded text regions, disrupting visual understanding. In contrast, Qwen's vision encoder handles text-embedded images robustly. Crucially, Prompt-in-Image reduces Qwen's modality gap, enhancing cross-modal alignment by unifying information processing through a single modality.