White-box method ReXTrust achieves highest AUC (peak 93.0) on Gut-VLM across five VLMs, outperforming alternatives by statistically significant margins while black-box and some gray-box methods collapse on certain models.
Chaudhari, and Jean-Benoit Delbrouck
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
Introduces the SAGE South Asian GI endoscopy dataset and reports large performance drops in multi-class classifiers and large multimodal models due to geographic population shift.
RadSEM is a constrained LLM-assisted metric that rewrites radiology reports into atomic finding sentences, applies contradiction-constrained many-to-many matching, and computes an abnormal-focused weighted F1 score.
RAD3D-Prefix is a diagnostic-prior conditioning framework for 3D CT report generation that integrates image embeddings with multi-label classification logits, showing that freezing larger LLMs and training only projection layers outperforms fine-tuning across scales.
ESC-RL improves RL for radiology reports via group-wise evidence-aware rewards (GEAR) and LLM-driven self-correcting preference learning (SPL), reaching state-of-the-art on two chest X-ray datasets.
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.
citing papers explorer
-
A Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy
White-box method ReXTrust achieves highest AUC (peak 93.0) on Gut-VLM across five VLMs, outperforming alternatives by statistically significant margins while black-box and some gray-box methods collapse on certain models.
-
SAGE: An Expert-Annotated South Asian GI Endoscopy Dataset for Multimodal Learning and Hallucination Analysis
Introduces the SAGE South Asian GI endoscopy dataset and reports large performance drops in multi-class classifiers and large multimodal models due to geographic population shift.
-
RadSEM: A Finding-by-Finding Metric for Clinical Consistency in Radiology Reports
RadSEM is a constrained LLM-assisted metric that rewrites radiology reports into atomic finding sentences, applies contradiction-constrained many-to-many matching, and computes an abnormal-focused weighted F1 score.
-
Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors
RAD3D-Prefix is a diagnostic-prior conditioning framework for 3D CT report generation that integrates image embeddings with multi-label classification logits, showing that freezing larger LLMs and training only projection layers outperforms fine-tuning across scales.
-
Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning
ESC-RL improves RL for radiology reports via group-wise evidence-aware rewards (GEAR) and LLM-driven self-correcting preference learning (SPL), reaching state-of-the-art on two chest X-ray datasets.
-
CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation
CXRMate-2 improves chest X-ray report generation via temporal embeddings and tractable RL, delivering metric gains and 45% acceptability in radiologist review with no significant preference difference on most findings.