I'm a Ph.D. student at Cornell University and Weill Cornell Medicine, where I work with
Yifan Peng
in the Peng Lab
on language models for clinical decision-making. My work is supported by an
NSF Graduate Research Fellowship.
My primary line of research studies how language models can support clinical decision-making by following
clinical practice guidelines, whose decision logic is spread across the text and flowcharts of long documents.
I build systems that extract this logic into decision trees and evaluate how accurately language models follow
them for patient cases. Secondarily, I work on natural language processing methods for clinical text.
Language Models for Clinical Decision-Making
My work here broadly draws on the following sub-areas:
Multi-Agent SystemsCoordinating language model agents to extract the decision logic in a clinical practice guideline into a decision tree, and then to traverse that tree for a patient case (CPGPrompt).
Benchmarking and EvaluationMeasuring how accurately language models follow guideline decision trees, with a multimodal benchmark of patient vignettes and an evaluation harness that scores each step of the path as well as the final recommendation.
Fine-TuningTraining small open models to follow the decision paths of new clinical guidelines more closely.
AnalysisPlacing hospital patients on the branches of a guideline tree from their records, to measure how closely the care they received follows the guideline.
Example
An ankle X-ray series is indicated only when the patient has pain in the malleolar zone
and any one of these findings is present:
bone tenderness along the posterior edge or at the tip of the lateral malleolus,
bone tenderness along the posterior edge or at the tip of the medial malleolus, or
inability to bear weight for four steps both immediately after the injury and in the emergency department.
If none of these findings is present, an X-ray is not needed.
Adapted from the ankle portion of the Ottawa Ankle Rules (Stiell et al., JAMA 1993) and simplified for illustration. All patient details are invented.
Nov 2026Two papers were accepted at IEEE BigData 2026, on capacity planning for clinical LLM serving and on explainable suicide risk assessment.
Jul 2026Presented our survey on MLLM-based visually rich document understanding at ACL 2026 in San Diego.
Publications
Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt ComplexityWe compare large language models with a fine-tuned RoBERTa model for extracting the circumstances of suicides from death investigation narratives, and test when detailed coding guidelines in the prompt help.G. Martin, X.Z. Feng, Y. PengIEEE International Conference on Healthcare Informatics (ICHI), 2026arXiv
Budget-Aware Routing for Long Clinical TextWe study how to choose which parts of a long clinical document to give a language model when its input length is capped, and propose a simple rule for picking the best selection strategy for each task.K. Qureshi, G. Martin, Y. PengFindings of the Association for Computational Linguistics (ACL), 2026
Capacity Planning for Resource-Constrained Clinical LLM ServingWe study how a hospital with limited computing hardware should divide it between small and large language models, and whether that choice matters more than how requests are routed between them.Y. Tang, G. Martin, Y. Zhang, Y. PengIEEE International Conference on Big Data (BigData), Special Session on Healthcare Data, 2026arXiv
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging TrendsWe survey how multimodal large language models are used to understand documents that combine text with visual layout, such as forms and scanned reports.Y. Ding, S. Luo, Y. Dai, Y. Jiang, Z. Li, Q. Sun, G. Martin, W. Liu, Y. PengFindings of the Association for Computational Linguistics (ACL), 2026
CPGPrompt: Translating Clinical Guidelines into Large Language Model-Executable Decision SupportIn this work, we convert clinical practice guidelines into decision trees and use a language model to walk through them for each patient case, producing recommendations that follow the guideline.R. Deng*, G. Martin*, T. Wang, G. Zhang, Y. Liu, C. Weng, Y. Wang, J. Rousseau, Y. PengJournal of the American Medical Informatics Association (JAMIA), 33(4), 2026
Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRAWe fine-tune a language model on several related tasks at once to assess suicide risk in social media posts and to explain each assessment with evidence from the post.X.Z. Feng, G. Martin, H. Dong, Y. PengIEEE International Conference on Big Data (BigData), BigData Challenge Cup, 2026arXiv
Reducing the Prevalence of Alcohol-Exposed Pregnancies in the United States: A Simulation Modeling StudyWe build a simulation model of US women of reproductive age to estimate how much different public health strategies could reduce alcohol-exposed pregnancies.R. Yaesoubi, M. Mahin, G. Martin, A. D. Paltiel, M. SharifiMedical Decision Making, 42(2), 2022
* equal contribution
Talks and Posters
Nov 2026Fine-Tuning Improves Path Adherence on Unseen Clinical Guidelines. AMIA NLP Working Group pre-symposium, Student Consortium, Dallas
Nov 2026Youth Suicide Risk Factor Discovery with LLM-Guided Topic Modeling. AMIA NLP Working Group pre-symposium, lightning talk, Dallas
Nov 2026Budget-Aware Routing for Long Clinical Text. AMIA 2026 Annual Symposium, Dallas
Jul 2026A Survey on MLLM-based Visually Rich Document Understanding. ACL 2026, poster, San Diego
Nov 2025Expanding Suicide-SDoH Coverage from Death Investigation Narratives. AMIA NLP Working Group pre-symposium, Graduate Student Consortium, Atlanta
Service
Reviewer, npj Digital Medicine
Reviewer, ACL Rolling Review
Fellowships
National Science Foundation Graduate Research Fellowship 2022
Caltech Summer Undergraduate Research Fellowship 2018
Before Cornell
I grew up in Singapore, with earlier stops at NASA's Jet Propulsion Laboratory building vision models for robotics and at
Locus Analytics, a systems
economics think tank, working as a data scientist for a few years. Just before Cornell I studied operations research
and statistics at Yale, after completing my undergraduate degree at Yale-NUS College.
Related Academic Interests
Systems thinking, causal inference, public policy, and election science.