Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| 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 |