The increasing adoption of AI-generated radiology reports necessitates robust methods for detecting hallucinations--false or unfounded statements that could impact patient care. We present ReXTrust, a novel framework for fine-grained hallucination detection in AI-generated radiology reports. Our approach leverages sequences of hidden states from large vision-language models to produce finding-level hallucination risk scores. We evaluate ReXTrust on a subset of the MIMIC-CXR dataset and demonstrate superior performance compared to existing approaches, achieving an AUROC of 0.8751 across all findings and 0.8963 on clinically significant findings. Our results show that white-box approaches leveraging model hidden states can provide reliable hallucination detection for medical AI systems, potentially improving the safety and reliability of automated radiology reporting.
@article{arxiv.2412.15264,
title = {ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports},
author = {Romain Hardy and Sung Eun Kim and Du Hyun Ro and Pranav Rajpurkar},
journal= {arXiv preprint arXiv:2412.15264},
year = {2025}
}