arXiv Computation and Language

Investigating LLM Capabilities on Long Context Comprehension for Clinical Question Answering

The study evaluates large language models (LLMs) on long-context comprehension for clinical question answering using patient Electronic Health Records (EHRs). It compares extractive, multiple-choice, and open-ended generative QA across various datasets, models, and metrics, including Retrieval Augmented Generation (RAG) and full-context prompting. Findings show that medically fine-tuned models do not outperform base models, smaller models memorize better, longitudinal notes help generative QA, and hybrid RAG with reranking outperforms full-context prompting, while revealing systematic failures that highlight the need for reasoning-appropriate metrics.

arXiv AI
Jul 9

Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

arXiv:2607. 06641v1 Announce Type: cross Abstract: Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance.

By Felix Feldman, Joshua Harris, Timothy Laurence, Leo Loman, Ollie Higgins, Fan Grayson, Poonam Soma, Bethany Pace-Bonello, Michael Borowitz, Toby Nonnenmacher
arXiv AI
Jun 16

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

arXiv:2606. 15735v1 Announce Type: cross Abstract: Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making.

By Jiyoun Kim, Muhan Yeo, Eunhye Jang, Jeewon Yang, Hangyul Yoon, Su Ji Lee, Hee Jo Han, Hee-Jae Jung, Doyun Kwon, Jun young Lee, Jaehun Lee, Jung-Oh Lee, Sunjun Kweon, Jong Hak Moon, Daseul Kim, Minjae Cho, Edward Choi
arXiv AI
Sep 25

A Living Benchmark for Information Retrieval from Electronic Health Records

The paper introduces BRIE, a continuously maintainable benchmark for evaluating large language models (LLMs) in electronic health record (EHR) information retrieval. It presents a scalable framework that automatically generates question–answer pairs from longitudinal EHR notes, validated by nineteen clinicians. The benchmark allows assessment of multiple inference strategies and highlights that state‑of‑the‑art LLMs often miss clinically important information, especially when synthesis across documents is required.

By Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T. Fisher, Sarita Khemani, Jerry Liu, Stephen Ma, Saloni K. Maharaj, Rita M. Pandya, Eduardo Perez-Guerrero, Priyanka Pillai, Lisa Shieh, David J. H. Wu, James Xie, James C. McAvoy, Teresa Nguyen, Jessica Tran, Lucy Yin, Bridget Lin, Alison Callahan, Jason A. Fries, Nigam H. Shah, Emily Alsentzer
Hugging Face Trending Papers
Sep 24

A Living Benchmark for Information Retrieval from Electronic Health Records

The paper introduces BRIE, a scalable framework that automatically creates question–answer pairs from longitudinal electronic health record notes, validated by nineteen clinicians. It offers a continuously maintainable benchmark for evaluating large language models in clinical settings, addressing limitations of manual, costly, and quickly outdated existing benchmarks. Experiments across nine LLMs and five inference strategies reveal that even state‑of‑the‑art systems often miss clinically important information, especially for synthesis‑heavy queries.

arXiv AI
Jul 13

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs

arXiv:2508. 14817v2 Announce Type: replace-cross Abstract: Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs).

By Skatje Myers, Dmitriy Dligach, Timothy A. Miller, Samantha Barr, James Landefeld, Yanjun Gao, Matthew Churpek, Anoop Mayampurath, Majid Afshar
arXiv AI
Sep 7

PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning

PetQA is a Korean long‑form question‑answering benchmark designed to assess veterinary knowledge and clinical reasoning in large language and vision‑language models. It comprises 10,076 text‑only and 8,751 multimodal QA pairs about dogs and cats, with expert veterinarian answers, and a test split called PetQA‑Bench that includes question type and clinical condition annotations. The study evaluates 18 models across zero‑shot, retrieval‑augmented generation, and supervised fine‑tuning settings using ROUGE, BERTScore, and LLM‑as‑a‑judge metrics, revealing current models’ strengths and limitations and underscoring the need for better adaptation methods for clinically reliable veterinary AI; translated versions in five languages are also provided.

By Taegyun Kim, Youngwook Ham, Jungwook Rhim, Ju-Hyun An, Sungkyu Park, Kunwoo Park
arXiv Computation and Language
Oct 21

Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing

The study evaluates small recurrent‑depth language models for multitask clinical text processing, fine‑tuning five models on nine datasets and testing on four unseen datasets. Across 13 tasks, Ouro‑1.4B‑Thinking outperformed Qwen3‑1.7B on 11 datasets, while Ouro‑2.6B‑Thinking matched Qwen3‑8B on most tasks, with the largest gains seen in inference and question answering. The results suggest recurrent‑depth architectures merit further controlled investigation for clinical NLP.

By Xi Yang, Guodong Liu, Cheng Peng, Kaleb Smith, Yingying Zhang, Xing He, Yi Guo, Jiang Bian, Haoteng Tang, Yonghui Wu