GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs

• URL: http://arxiv.org/abs/2509.25178v1
• Date: Mon, 29 Sep 2025 17:59:23 GMT
• Title: GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
• Authors: Aryan Yazdan Parast, Parsa Hosseini, Hesam Asadollahzadeh, Arshia Soltani Moakhar, Basim Azam, Soheil Feizi, Naveed Akhtar,
• Abstract summary: We introduce GHOST, a method designed to stress-test MLLMs by actively generating images that induce hallucination.<n>GHOST is fully automatic and requires no human supervision or prior knowledge.<n>We evaluate our method across a range of models, including reasoning models like GLM-4.1V-Thinking, and achieve a hallucination success rate exceeding 28%, compared to around 1% in prior data-driven discovery methods.
• Score: 61.829473661517675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the image. This weakness of MLLMs is currently studied using static benchmarks with fixed visual scenarios, which preempts the possibility of uncovering model-specific or unanticipated hallucination vulnerabilities. We introduce GHOST (Generating Hallucinations via Optimizing Stealth Tokens), a method designed to stress-test MLLMs by actively generating images that induce hallucination. GHOST is fully automatic and requires no human supervision or prior knowledge. It operates by optimizing in the image embedding space to mislead the model while keeping the target object absent, and then guiding a diffusion model conditioned on the embedding to generate natural-looking images. The resulting images remain visually natural and close to the original input, yet introduce subtle misleading cues that cause the model to hallucinate. We evaluate our method across a range of models, including reasoning models like GLM-4.1V-Thinking, and achieve a hallucination success rate exceeding 28%, compared to around 1% in prior data-driven discovery methods. We confirm that the generated images are both high-quality and object-free through quantitative metrics and human evaluation. Also, GHOST uncovers transferable vulnerabilities: images optimized for Qwen2.5-VL induce hallucinations in GPT-4o at a 66.5% rate. Finally, we show that fine-tuning on our images mitigates hallucination, positioning GHOST as both a diagnostic and corrective tool for building more reliable multimodal systems.

Related papers

• HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images [9.716231984097313]
  Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted in inherent language bias.<n>In this work, we design a novel pipeline to accurately synthesize Hallucination-Inducing Images (HIIs)<n>Using synthesized HIIs, we reveal a consistent scene-conditioned hallucination pattern.<n>Our method achieves up to a 38% improvement over the current state-of-the-art on standard hallucination benchmarks.
  arXiv  Detail & Related papers  (2026-02-11T02:11:02Z)
• What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models? [95.46087552542998]
  This paper introduces the Hallucination searching-based Object Probing Evaluation benchmark.<n>It aims to generate the most misleading distractors that can trigger hallucination in Large Vision-Language Models.<n> Experimental results show that HOPE leads to a precision drop of at least 9% and up to 23% across various state-of-the-art LVLMs.
  arXiv  Detail & Related papers  (2025-08-03T03:11:48Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [67.14942827452161]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs [15.479587108655393]
  Large Vision-Language Models (LVLMs) still face challenges with object hallucination.<n>Our work shifts the focus to the image input source, investigating how specific image tokens contribute to hallucinations.<n>We introduce EAZY, a novel, training-free method that automatically identifies and Eliminates hAllucinations by Zeroing out hallucinatorY image tokens.
  arXiv  Detail & Related papers  (2025-03-10T18:53:39Z)
• Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models [57.58426038241812]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in complex multimodal tasks.<n>These models still suffer from hallucinations when required to implicitly recognize or infer diverse visual entities from images.<n>We propose a novel visual question answering (VQA) benchmark that employs contextual reasoning prompts as hallucination attacks.
  arXiv  Detail & Related papers  (2024-12-29T23:56:01Z)
• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models [59.05674402770661]
  This work introduces VideoHallucer, the first comprehensive benchmark for hallucination detection in large video-language models (LVLMs) VideoHallucer categorizes hallucinations into two main types: intrinsic and extrinsic, offering further subcategories for detailed analysis.
  arXiv  Detail & Related papers  (2024-06-24T06:21:59Z)
• AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models [91.78328878860003]
  Large vision-language models (LVLMs) are prone to hallucinations. benchmarks often rely on hand-crafted corner cases whose failure patterns may not generalize well. We develop AutoHallusion, the first automated benchmark generation approach.
  arXiv  Detail & Related papers  (2024-06-16T11:44:43Z)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
  We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback.<n>We generate a small-size hallucination annotation dataset by proprietary models.<n>Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
  arXiv  Detail & Related papers  (2024-04-22T14:46:10Z)
• Detecting and Preventing Hallucinations in Large Vision Language Models [4.7264116948935975]
  M-HalDetect is the first multi-modal hallucination detection dataset for detailed image descriptions. We train fine-grained multi-modal reward models from InstructBLIP and evaluate their effectiveness with best-of-n rejection sampling. We find that our reward model generalizes to other multi-modal models, reducing hallucinations in LLaVA and mPLUG-OWL by 15% and 57% respectively.
  arXiv  Detail & Related papers  (2023-08-11T21:35:20Z)
• Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training [66.0036211069513]
  Large-scale vision-language pre-trained models are prone to hallucinate non-existent visual objects when generating text. We show that models achieving better scores on standard metrics could hallucinate objects more frequently. Surprisingly, we find that patch-based features perform the best and smaller patch resolution yields a non-trivial reduction in object hallucination.
  arXiv  Detail & Related papers  (2022-10-14T10:27:22Z)

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.