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

• URL: http://arxiv.org/abs/2508.01678v1
• Date: Sun, 03 Aug 2025 09:11:18 GMT
• Title: Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models
• Abstract summary: Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information.<n>We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images.<n>We evaluate this method on three popular open-source VLMs: Qwen2.5-VL, LLaVA-1.5, and InstructBLIP.
• Score: 12.215295420714787
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token [4.2940165358265086]
  Hallucinations remain a persistent challenge for vision-language models (VLMs)<n>We investigate whether hallucination risk can be predicted before any token is generated by probing a model's internal representations in a single forward pass.
  arXiv  Detail & Related papers  (2026-03-05T18:36:31Z)
• Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models [0.7919969809015935]
  Vision-Language Models (VLMs) often hallucinate objects that are not present in the input image.<n>We propose Spatial Credit Redistribution (SCR), a training-free-time inference method.<n>SCR achieves a better trade-off between hallucination reduction, generation quality, and latency.
  arXiv  Detail & Related papers  (2026-02-25T23:08:31Z)
• Feedback-Driven Vision-Language Alignment with Minimal Human Supervision [11.012355590697064]
  We introduce SVP (Sampling-based Visual Projection), a novel framework that enhances vision-language alignment without relying on manually curated text-image pairs or preference annotation.<n>We evaluate our approach across six key areas: captioning, referring, visual question answering, multitasking, hallucination control, and object recall.<n>Results demonstrate significant improvements, including a 14 % average improvement in captioning tasks, up to 12 % increase in object recall, and significantly reduced hallucinations.
  arXiv  Detail & Related papers  (2025-01-08T15:32:12Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance [67.26434607115392]
  Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on images and ineffective visual comprehension. We propose LACING to address the language bias of LVLMs with muLtimodal duAl-attention meChanIsm (MDA) aNd soft-image Guidance (IFG)
  arXiv  Detail & Related papers  (2024-11-21T16:33:30Z)
• Attention Prompting on Image for Large Vision-Language Models [63.794304207664176]
  We propose a new prompting technique named Attention Prompting on Image. We generate an attention heatmap for the input image dependent on the text query with an auxiliary model like CLIP. Experiments on various vison-language benchmarks verify the effectiveness of our technique.
  arXiv  Detail & Related papers  (2024-09-25T17:59:13Z)
• Multi-Modal Hallucination Control by Visual Information Grounding [121.6983694815504]
  We show that Generative Vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that are not always grounded in the input image. We introduce Multi-Modal Mutual-Information Decoding (M3ID), a new sampling method for prompt amplification. M3ID amplifies the influence of the reference image over the language prior, hence favoring the generation of tokens with higher mutual information with the visual prompt.
  arXiv  Detail & Related papers  (2024-03-20T22:05:18Z)
• Mitigating Hallucination in Visual Language Models with Visual Supervision [33.05550629039951]
  Large vision-language models (LVLMs) suffer from hallucination a lot. Key problem lies in its weak ability to comprehend detailed content in a multi-modal context. In this paper, we bring more detailed vision annotations and more discriminative vision models to facilitate the training of LVLMs.
  arXiv  Detail & Related papers  (2023-11-27T09:30:02Z)
• PuMer: Pruning and Merging Tokens for Efficient Vision Language Models [41.81484883647005]
  PuMer is a framework that uses text-informed Pruning and modality-aware Merging strategies to progressively reduce the tokens of input image and text. PuMer inference increases throughput by up to 2x and reduces memory footprint by over 50% while incurring less than a 1% accuracy drop.
  arXiv  Detail & Related papers  (2023-05-27T17:16:27Z)
• Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition [92.6211155264297]
  Vision models have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. Recent vision models suffer from two problems: (1) the pure vision-based query results in attention drift, which usually causes poor recognition and is summarized as linguistic insensitive drift (LID) problem in this paper. We propose a $textbfL$inguistic $textbfP$erception $textbfV$ision model (LPV) which explores the linguistic capability of vision model for accurate text recognition.
  arXiv  Detail & Related papers  (2023-05-09T02:52:47Z)
• Learning to Decompose Visual Features with Latent Textual Prompts [140.2117637223449]
  We propose Decomposed Feature Prompting (DeFo) to improve vision-language models. Our empirical study shows DeFo's significance in improving the vision-language models.
  arXiv  Detail & Related papers  (2022-10-09T15:40:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.