arXiv AI August 28, 2026 By Jin Mu, Guanhua Chen

Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 20

Large Language Models as Unified Multimodal Learners for Clinical Prediction

arXiv:2607. 15380v1 Announce Type: cross Abstract: Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities.

By Ajay Madhavan Ravichandran, Bilgin Osmandoja, Klemens Budde, Klaus Netter, Tobias Strapatsas, Aljoscha Burchardt, Sebastian M\"oller, Roland Roller

llms fine-tuning multimodal

arXiv Machine Learning

Sep 15

Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV

arXiv:2609.15713v1 Announce Type: new Abstract: Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods...

By Mohamad Najafi, Hongyun Fu, Mathias Brochhausen, Jian Wu, Yaohang Li

llms rag safety

arXiv Machine Learning

Sep 25

Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER

This study benchmarks transformer models for Bangla medical named entity recognition (NER), comparing BanglaBERT, multilingual BERT (mBERT), XLM‑RoBERTa, and GPT‑4o mini under zero‑shot and few‑shot prompting. Across a full test set of 3,179 samples, fine‑tuned XLM‑RoBERTa achieves a new state‑of‑the‑art F1‑score of 0.5959, while BanglaBERT lags with 0.4937, suggesting that domain diversity outweighs language specificity. The analysis shows high performance on Medicine and Specialist entities (F1 > 0.83) but lower accuracy on Symptoms (F1 0.4367), and demonstrates that fine‑tuned transformers outperform prompt‑only approaches by a factor of 3.76.

By Rakib Abdullah, Md. Maruful Islam Maruf

llms nlp fine-tuning benchmarks

arXiv AI

Jun 19

CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions

arXiv:2604. 05435v2 Announce Type: replace Abstract: Incomplete or inconsistent discharge documentation drives care fragmentation and avoidable readmissions.

By Akshat Dasula, Prasanna Desikan, Jaideep Srivastava, Shivali Dalmia, Abhishek Mukherji

llms benchmarks safety

arXiv AI

Jun 30

Primary ICD Category Prediction using LLM-based Probing

arXiv:2606. 28798v1 Announce Type: new Abstract: Objective: ICD codes are central to reimbursement, research, and population health surveillance, yet automated coding systems often struggle to integrate diagnostic signals from both clinical narratives and structured electronic health record (EHR) variables.

By Chengyuan Liu, Xinyue Zhang, Yao Li, Guanting Chen

llms rag multimodal

arXiv Machine Learning

Oct 2

Learning to Select Source-Traceable Evidence for Language-Model Prediction from Irregular Clinical Time Series

arXiv:2605.20292v2 Announce Type: replace Abstract: Numerical time-series models effectively process irregular electronic health record (EHR) trajectories, but do not expose which temporal patterns s...

By Kwanhyung Lee, Juhwan Choi, Jongheon Kim, Joohyung Lee, Hyeongwon Jang, Jeonguk Lee, Jisoo Jung, Eunho Yang

llms benchmarks

One email a morning, machine-written

Related stories

Large Language Models as Unified Multimodal Learners for Clinical Prediction

Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV

Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER

CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions

Primary ICD Category Prediction using LLM-based Probing

Learning to Select Source-Traceable Evidence for Language-Model Prediction from Irregular Clinical Time Series