arXiv Machine Learning October 5, 2026 By Aishik Nagar, Abhishek Vaidyanathan, Arun-Kumar Kaliya-Perumal, Elijah Tzen Hsuen Boey, Stefan Winkler

Clinical Concept Centers in LLMs

Read the original on arXiv Machine Learning →

The paper investigates whether clinical concepts are represented as distinct, causally influential centers within the latent space of large language models (LLMs). By evaluating eleven open-weight LLMs, the authors discover that each model contains dedicated clinical concept centers that are interpretable, activate only on relevant clinical narratives, and drive model behavior in both constrained and open-ended contexts. These centers can be leveraged for evaluation and performance improvement, as steering models along them enhances downstream clinical outcomes and aligns with clinician preferences.

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 Machine Learning.

arXiv AI

Jun 8

When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations

arXiv:2606. 07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.

By Mahdi Alkaeed

llms nlp benchmarks safety

arXiv Machine Learning

Jun 15

Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops

arXiv:2606. 14149v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved.

By Muhammad Osama, Maheera Amjad, Zartasha Mustansar, Arslan Shaukat, Muhammad U. S. Khan

llms agents safety

arXiv Machine Learning

Aug 7

Clinician input steers AI toward accurate and harmful recommendations

arXiv:2603. 14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions.

By Ivan Lopez, Selin S. Everett, Bryan J. Bunning, April S. Liang, Dong Han Yao, Shivam C. Vedak, Kameron C. Black, Sophie Ostmeier, Stephen P. Ma, Emily Alsentzer, Jonathan H. Chen, Akshay S. Chaudhari, Eric Horvitz

llms safety

arXiv AI

5d ago

Scaling Clinical Judgment to Evaluate Medical AI

The paper introduces PrecepTron, a 32‑billion‑parameter language model fine‑tuned with low‑rank adaptation to evaluate clinical reasoning in large language models (LLMs) at a physician level. It also releases GRAND‑ROUNDS, a benchmark of 9,217 scored responses from 160 clinicians across seven studies. Using PrecepTron, the authors replicate key findings from major medical AI studies and explore new questions about LLM diagnostic accuracy, demonstrating that fine‑tuned models can provide consistent, scalable physician‑level scoring.

By Thomas A. Buckley, Zahir Kanjee, Peter G. Brodeur, Byron Crowe, Anthony M. Pettinato, Aashna P. Shah, Adrian D. Haimovich, Liam G. McCoy, Daniel Restrepo, Jason A. Freed, Ethan Goh, Jonathan H. Chen, Laura Zwaan, Katherine E. Goodman, Daniel J. Morgan, Raja-Elie E. Abdulnour, Adam Rodman, Arjun K. Manrai

llms fine-tuning benchmarks

arXiv Machine Learning

Sep 1

Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

arXiv:2601.12868v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in high-stakes settings where demographic attributes such as race and ethnicity may be expl...

By Shiyue Hu, Ruizhe Li, Yanjun Gao

llms nlp safety

arXiv Machine Learning

Jun 24

PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models

arXiv:2606. 24102v1 Announce Type: cross Abstract: Most electronic health record (EHR) foundation models encode clinical events as discrete event tokens from a fixed vocabulary and therefore cannot directly represent events containing unseen concepts or new combinations of concepts and attributes such as numeric values.

By Lin Lawrence Guo, Adam Paul Yan, Emily Vettese, Lillian Sung

One email a morning, machine-written

Related stories

When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations

Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops

Clinician input steers AI toward accurate and harmful recommendations

Scaling Clinical Judgment to Evaluate Medical AI

Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models