9 papers
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
Ta Duc Huy, Trang Nguyen, Townim Chowdhury +5
Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common entropy-based methods, such as Semantic Entropy (SE), rel…
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen +8
Large vision-language models (LVLMs) achieve strong performance on visual reasoning tasks but remain highly susceptible to hallucination. Existing detection methods predominantly r…
Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Models
Abin Shoby, Ta Duc Huy, Tuan Dung Nguyen +6
Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one mus…
Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs
Dung Nguyen, Minh Khoi Ho, Huy Ta +11
Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradic…
From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesis
Nayu Dong, Townim Chowdhury, Hieu Phan +3
The scarcity of annotated Magnetic Resonance Imaging (MRI) tumor data presents a major obstacle to accurate and automated tumor segmentation. While existing data synthesis methods…
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
Townim Faisal Chowdhury, Vu Minh Hieu Phan, Kewen Liao +5
Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interp…