GraphWalker: Graph-Guided In-Context Learning for Clinical Reasoning on Electronic Health Records

ACL ARR 2026 January Submission8987 Authors

Keywords: In-Context Learning, Electronic Health Records, Large Language Models, Healthcare AI

Abstract:

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://anonymous.4open.science/status/GraphWalker-4473.

Paper Type: Long

Research Area: Clinical and Biomedical Applications

Research Area Keywords: clinical and biomedical language models, clinical decision support

Languages Studied: English, Chinese

Submission Number: 8987