Objective To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy of black-box vision-language models (VLMs) in radiologic image-based visual question answering (VQA). Materials and methods This retrospective study evaluated DSE using two publicly available, de-identified datasets: the VQA-Med 2019 benchmark (500 images with clinical questions and short-text answers) and a diagnostic radiology dataset (206 cases: 60 computed tomography scans, 60 magnetic resonance images, 60 radiographs, 26 angiograms) with corresponding ground-truth diagnoses. GPT-4o and GPT-4.1 (Generative Pretrained Transformer) answered each question 15 times using a temperature of 1.0. Baseline accuracy was determined using low-temperature answers (0.1). Meaning-equivalent responses were grouped using bidirectional entailment checks, and DSE was computed from the relative frequencies of the resulting semantic clusters. Accuracy was recalculated after excluding questions with DSE > 0.6 or > 0.3. p values and 95% confidence intervals were obtained using bootstrap resampling and a Bonferroni-corrected threshold of p < 0.004 for statistical significance. Results Across 706 image–question pairs, baseline accuracy was 51.7% for GPT-4o and 54.8% for GPT-4.1. After filtering out high-entropy questions (DSE > 0.3), accuracy on the remaining questions was 76.3% (retained questions: 334/706) for GPT-4o and 63.8% (retained questions: 499/706) for GPT-4.1 (both p < 0.001). Accuracy gains were observed across both datasets and largely remained statistically significant after Bonferroni correction. Conclusion DSE enables reliable hallucination detection in black-box VLMs by quantifying semantic inconsistency. This method significantly improves diagnostic answer accuracy and offers a filtering strategy for clinical VLM applications. Key Points <Emphasis Type="BoldItalic">Question</Emphasis> Can DSE identify hallucination-prone questions and improve the reliability of black-box vision–language models in radiologic image-based VQA? <Emphasis Type="BoldItalic">Findings</Emphasis> DSE filtering at a 0.3 threshold increased GPT-4o accuracy from 51.7% to 76.3% and GPT-4.1 from 54.8% to 63.8%, while answering fewer questions. <Emphasis Type="BoldItalic">Clinical relevance</Emphasis> Integrating DSE as a black-box uncertainty filter enables selective answering and explicit uncertainty display for radiology vision–language tools, supporting safer diagnostic use, mitigating hallucinations, and improving clinicians’ trust in AI-assisted image interpretation. Graphical Abstract

Hallucination filtering in radiology vision-language models using discrete semantic entropy

期刊论文
出版模式：

开放获取
发表日期：

2026年2月20日

查看全文

Patrick Wienholt,
Sophie Caselitz,
Robert Siepmann,
Philipp Bruners,
Keno Bressem,
Christiane Kuhl,
Jakob Nikolas Kather,
Sven Nebelung,
Daniel Truhn

摘要

Objective

To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy of black-box vision-language models (VLMs) in radiologic image-based visual question answering (VQA).

Materials and methods

This retrospective study evaluated DSE using two publicly available, de-identified datasets: the VQA-Med 2019 benchmark (500 images with clinical questions and short-text answers) and a diagnostic radiology dataset (206 cases: 60 computed tomography scans, 60 magnetic resonance images, 60 radiographs, 26 angiograms) with corresponding ground-truth diagnoses. GPT-4o and GPT-4.1 (Generative Pretrained Transformer) answered each question 15 times using a temperature of 1.0. Baseline accuracy was determined using low-temperature answers (0.1). Meaning-equivalent responses were grouped using bidirectional entailment checks, and DSE was computed from the relative frequencies of the resulting semantic clusters. Accuracy was recalculated after excluding questions with DSE > 0.6 or > 0.3. p values and 95% confidence intervals were obtained using bootstrap resampling and a Bonferroni-corrected threshold of p < 0.004 for statistical significance.

Results

Across 706 image–question pairs, baseline accuracy was 51.7% for GPT-4o and 54.8% for GPT-4.1. After filtering out high-entropy questions (DSE > 0.3), accuracy on the remaining questions was 76.3% (retained questions: 334/706) for GPT-4o and 63.8% (retained questions: 499/706) for GPT-4.1 (both p < 0.001). Accuracy gains were observed across both datasets and largely remained statistically significant after Bonferroni correction.

Conclusion

DSE enables reliable hallucination detection in black-box VLMs by quantifying semantic inconsistency. This method significantly improves diagnostic answer accuracy and offers a filtering strategy for clinical VLM applications.

Key Points

Question Can DSE identify hallucination-prone questions and improve the reliability of black-box vision–language models in radiologic image-based VQA?

Findings DSE filtering at a 0.3 threshold increased GPT-4o accuracy from 51.7% to 76.3% and GPT-4.1 from 54.8% to 63.8%, while answering fewer questions.

Clinical relevance Integrating DSE as a black-box uncertainty filter enables selective answering and explicit uncertainty display for radiology vision–language tools, supporting safer diagnostic use, mitigating hallucinations, and improving clinicians’ trust in AI-assisted image interpretation.

Graphical Abstract