paper-with-me

Papers

CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base

2025-02-18 · Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu, Shuai Zhao, Thong Nguyen, Anh Tuan Luu

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination where non-existent objects or incorrect attributes are fabricated in generated descriptions. Existing detection methods achieve strong performance but rely heavily on expensive API calls and iterative LVLM-based validation, making them impractical for large-scale or offline use. To address these limitations, we propose CutPaste\&Find, a lightweight and training-free framework for detecting hallucinations in LVLM-generated outputs. Our approach leverages off-the-shelf visual and linguistic modules to perform multi-step verification efficiently without requiring LVLM inference. At the core of our framework is a Visual-aid Knowledge Base that encodes rich entity-attribute relationships and associated image representations. We introduce a scaling factor to refine similarity scores, mitigating the issue of suboptimal alignment values even for ground-truth image-text pairs. Comprehensive evaluations on benchmark datasets, including POPE and R-Bench, demonstrate that CutPaste\&Find achieves competitive hallucination detection performance while being significantly more efficient and cost-effective than previous methods.

📄 PDF Abstract BibTeX arXiv:2502.12591

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeHallucinationMultimodal ReasoningObject Hallucination

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models

2026-05-12 · Runhe Lai, Xinhua Lu, Yanqi Wu, Jinlun Ye 외 arxiv

Multimodal large language models (MLLMs) have achieved remarkable progress, yet the object hallucination remains a critical challenge for reliable deployment. In this paper, we present an in-depth analysis of instruction…

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

2021-04-08 · CVPR 2021 1 · Chun-Liang Li, Kihyuk Sohn, Jinsung Yoon, Tomas Pfister

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detector…

Anomaly ClassificationAnomaly DetectionData AugmentationDefect Detection+4

V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention

2025-12-03 · Nan Sun, Zhenyu Zhang, Xixun Lin, Kun Wang 외 arxiv

Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domain…

Detecting and Evaluating Medical Hallucinations in Large Vision Language Models

2024-06-14 · Jiawei Chen, Dingkang Yang, Tong Wu, Yue Jiang 외

Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these models inherit the robust capabilities of …

HallucinationMedical Visual Question AnsweringQuestion AnsweringVisual Question Answering

EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors

2026-04-03 · Ryuhei Miyazato, Shunsuke Kitada, Kei Harada arxiv

Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using…

Ensemble Learning