Salvato in:
Dettagli Bibliografici
Autori principali: Fang, Yue, Liao, Weibin, Guo, Yuxin, Gao, Jiaran, Ding, Hongxin, Zhang, Jinyang, Jiang, Xinke, Yang, Zhibang, Zhao, Junfeng, Wang, Yasha, Ma, Liantao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.06684
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918434381496320
author Fang, Yue
Liao, Weibin
Guo, Yuxin
Gao, Jiaran
Ding, Hongxin
Zhang, Jinyang
Jiang, Xinke
Yang, Zhibang
Zhao, Junfeng
Wang, Yasha
Ma, Liantao
author_facet Fang, Yue
Liao, Weibin
Guo, Yuxin
Gao, Jiaran
Ding, Hongxin
Zhang, Jinyang
Jiang, Xinke
Yang, Zhibang
Zhao, Junfeng
Wang, Yasha
Ma, Liantao
contents Clinical Reasoning on Electronic Health Records (EHRs) is a fundamental yet challenging task in modern healthcare. While in-context learning (ICL) offers a promising inference-time adaptation paradigm for large language models (LLMs) in EHR reasoning, existing methods face three fundamental challenges: (1) Perspective Limitation, where data-driven similarity fails to align with LLM reasoning needs and model-driven signals are constrained by limited clinical competence; (2) Cohort Awareness, as demonstrations are selected independently without modeling population-level structure; and (3) Information Aggregation, where redundancy and interaction effects among demonstrations are ignored, leading to diminishing marginal gains. To address these challenges, we propose GraphWalker, a principled demonstration selection framework for EHR-oriented ICL. GraphWalker (i) jointly models patient clinical information and LLM-estimated information gain by integrating data-driven and model-driven perspectives, (ii) incorporates Cohort Discovery to avoid noisy local optima, and (iii) employs a Lazy Greedy Search with Frontier Expansion algorithm to mitigate diminishing marginal returns in information aggregation. Extensive experiments on multiple real-world EHR benchmarks demonstrate that GraphWalker consistently outperforms state-of-the-art ICL baselines, yielding substantial improvements in clinical reasoning performance. Our code is open-sourced at https://github.com/PuppyKnightUniversity/GraphWalker
format Preprint
id arxiv_https___arxiv_org_abs_2604_06684
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GraphWalker: Graph-Guided In-Context Learning for Clinical Reasoning on Electronic Health Records
Fang, Yue
Liao, Weibin
Guo, Yuxin
Gao, Jiaran
Ding, Hongxin
Zhang, Jinyang
Jiang, Xinke
Yang, Zhibang
Zhao, Junfeng
Wang, Yasha
Ma, Liantao
Machine Learning
Clinical Reasoning on Electronic Health Records (EHRs) is a fundamental yet challenging task in modern healthcare. While in-context learning (ICL) offers a promising inference-time adaptation paradigm for large language models (LLMs) in EHR reasoning, existing methods face three fundamental challenges: (1) Perspective Limitation, where data-driven similarity fails to align with LLM reasoning needs and model-driven signals are constrained by limited clinical competence; (2) Cohort Awareness, as demonstrations are selected independently without modeling population-level structure; and (3) Information Aggregation, where redundancy and interaction effects among demonstrations are ignored, leading to diminishing marginal gains. To address these challenges, we propose GraphWalker, a principled demonstration selection framework for EHR-oriented ICL. GraphWalker (i) jointly models patient clinical information and LLM-estimated information gain by integrating data-driven and model-driven perspectives, (ii) incorporates Cohort Discovery to avoid noisy local optima, and (iii) employs a Lazy Greedy Search with Frontier Expansion algorithm to mitigate diminishing marginal returns in information aggregation. Extensive experiments on multiple real-world EHR benchmarks demonstrate that GraphWalker consistently outperforms state-of-the-art ICL baselines, yielding substantial improvements in clinical reasoning performance. Our code is open-sourced at https://github.com/PuppyKnightUniversity/GraphWalker
title GraphWalker: Graph-Guided In-Context Learning for Clinical Reasoning on Electronic Health Records
topic Machine Learning
url https://arxiv.org/abs/2604.06684