arXiv Computation and Language September 24, 2026 By Chenxuan Li, Xinrong Chen, Luyan Zhang, Peidong Jia, Runfan Zheng, Zhongyu Zhao, Xuecheng Shang, Peixing Wan

Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue

Read the original on arXiv Computation and Language →

The paper introduces Expected‑Severity‑Risk (ESR), a new objective for selecting questions in proactive medical dialogue that prioritizes reducing the expected severity of diagnostic errors rather than merely uncertainty. ESR uses population statistics to marginalize over possible answers and distills its rankings into a prefix‑only language policy, enabling deployment without teacher‑side risk computation. Experiments on DDxPlus show ESR cuts high‑severity diagnostic misses by 29.5% and boosts accuracy while adding only 0.14 extra questions per dialogue.

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 Computation and Language.

agents

arXiv Machine Learning

Sep 24

PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue

arXiv:2609.27987v1 Announce Type: new Abstract: Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask...

By Chenxuan Li, Jiayi Wan, Xinrong Chen, Zhongyu Zhao, Xuecheng Shang, Peixing Wan

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 22

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

arXiv:2607. 18999v1 Announce Type: cross Abstract: Multi-turn medical consultation agents must decide what to ask, adapt to patient responses, and determine when the collected evidence is sufficient.

By Guofeng Zhang, Yizeng Quan, Huaiyi Fang, Jianwei Lv, Jinyao Liu, Xunxu Duan, Lening An, Yu Ouyang, Junfeng Wang

agents

arXiv AI

Aug 11

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

arXiv:2608. 09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.

By Maryam Tahermazandarani, Adnan Mahmood, Fahmida Islam, Quan Z. Sheng

llms nlp

arXiv AI

Sep 4

MIRA: A Bilingual Benchmark for Medical Information Response Audit

MIRA is a bilingual benchmark that evaluates whether large language models (LLMs) provide consistent medical information across different user phrasings, languages, and health literacy levels. It contains 4,320 prompts derived from 60 medically reviewed low‑risk health questions and reveals that models tend to omit key information and offer fewer concrete next steps when responding to low health‑literacy signals, a phenomenon termed Differential Information Dilution (DID). A knowledge‑guided mitigation prompt can reduce this dilution for most models, notably improving Claude and Qwen.

By Mengyu Xu, Qiaoxin Yang, Qianqian Wang, Xiwei Dai, Weiyi Wu, Chongyang Gao

llms benchmarks safety

arXiv AI

Aug 21

A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

arXiv:2608. 19875v1 Announce Type: cross Abstract: Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropriate response.

By Mahyar Abbasian, Saba A. Farahani, Arshia Ilaty, Hung Cao, Ramesh Jain, Amir M. Rahmani

llms agents benchmarks safety

arXiv AI

Aug 3

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support

arXiv:2607. 28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning.

By Shayndhan Sivanathan, Shravan Nageswaran, Mehdi Zadem, Ryaan Sultan, Nicolas von Mallinckrodt, Max Solovyev, Alexey Matyushkin, Sumon Sadhu, Gabriele C DeLuca, Sanjeeva Jeyaretna, James Hillis, Manoj Ramachandran, Prakash Jayakumar

llms agents safety

One email a morning, machine-written

Related stories

PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

MIRA: A Bilingual Benchmark for Medical Information Response Audit

A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support