arXiv:2608.23248v1 Announce Type: cross
Abstract: Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured...
By Siri Willems, James Butterworth, Lore Goetschalckx, Peter Vrancx, Philippe Modard, Elke Giets, Ludovic Denoyer
arXiv:2608.20887v1 Announce Type: cross
Abstract: Automatic Medical Coding (AMC), which assigns standardized International Classification of Diseases (ICD) codes to clinical notes, is essential for m...
By Xubin Chen, Yipeng Zhou, Wen Sun, Chengkai Huang, Xiaoming Fu, Quan Z. Sheng
The paper introduces CAST, a concept-guided artifact suppression tuning framework that uses sparse autoencoders to identify and suppress note-specific artifacts in clinical language models. CAST labels latent features with an LLM-assisted pipeline and ICD‑10 constraints, then fine‑tunes the model while providing post‑hoc per‑concept attributions for auditability. In experiments on MIMIC‑IV discharge‑note mortality prediction, CAST outperforms standard fine‑tuned encoders and competes with strong LLM baselines while offering a feature‑level audit trail of clinical concepts and suppressed artifacts.
By Jin Mu, Guanhua Chen
MedHal is a large-scale synthetic dataset created to detect hallucinations in medical AI-generated text. It includes diverse medical sources and tasks that cover both intrinsic and extrinsic hallucinations, providing a substantial volume of samples for training. The authors demonstrate that models trained on MedHal outperform general-purpose hallucination detectors, highlighting its usefulness for medical AI development.
By Fabrice Lamarche, Gaya Mehenni, Neshat Elhami Fard, Odette Rios-Ibacache, Li Ming Wang, John Kildea, Amal Zouaq
arXiv:2609.38543v1 Announce Type: new
Abstract: Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time...
By Lukas Thede, Yash Kumar Atri, David Chen, Danielle Bitterman, Matthias Bethge, Tom Hartvigsen, Zeynep Akata
arXiv:2605. 28910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications.
By Shamanth Kuthpadi Seethakantha, Dung Ngoc Thai, Vara Prasad Gudi, Simran Tiwari, Rami Matar, Avijit Mitra, Wenlong Zhao, Andrew McCallum, Wael Salloum