cs.CVNov 11, 2026

MAGIC: Modality-Aware Gini Inspection for Clinical Hallucination Detection in LMMs

Authors: Sachin Acharya, Niyoj Oli, Shishir Adhikari, Aminu Lawal, Yash Raj Shrestha, Prashnna K Gyawali, Binod Bhattarai

Organizations: Nepal Applied Mathematics and Informatics Institute for research, Nepal · Fogsphere (Redev.AI Ltd, UK) · Global College of Technology, Nepal · University of Aberdeen, UK · 

Abstract

Recent advances in medical large multimodal models (LMMs) have brought promising progress to clinical decision support, yet hallucination, the generation of confident but clinically unverifiable outputs, poses a critical threat to the reliability demanded in high-stakes medical settings. Existing hallucination detection methods, predominantly designed for unimodal settings, fail to capture the visual-linguistic dynamics inherent to medical imaging. We formulate the problem of hallucination detection in LMMs as disproportionate distribution of attention weights across the modalities during answer token generation. We quantify modality-specific attention concentration across layers and heads using the Gini coefficient and demonstrate statistically significant redistribution of attention mass between visual and textual tokens in hallucinated responses. We leverage these features to train a logistic regression-based classifier and evaluate it on two medical LMMs across three medical imaging modalities, demonstrating that our method achieves competitive or superior performance against contemporary hallucination detection baselines.

Figures & tables

Explore similar work

CardsList
  1. VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering

    May 20, 2026Jiayi Chen, Benteng Ma, Zehui Liao +3Hallucination Detection in VLMsHealthcare

  2. HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models

    Jul 23, 2026Weilin Jin, Mingyu Wang, Wenbo Li +5Hallucination Detection in VLMsMultimodal Hallucination

  3. Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty

    Jun 26, 2026Xiao Song, Haonan Qin, Zhaoxu Zhang +3Hallucination Detection in VLMsVLM Hallucination