ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
Journal:
arXiv
Published Date:
Dec 17, 2024
Abstract
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.
