GPT-RagAD: Two-layer Retrieval-Augmented Multilingual Diagnosis System

Xinyi Liu, Dachun Sun, Yi R. Fung, Dilek Hakkani-Tür, Tarek Abdelzaher
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:152-166, 2026.

Abstract

We introduce GPT-RagAD, a multilingual, zero-shot automated diagnosis system that achieves high accuracy without relying on real patient data. GPT-RagAD adopts a two-layer Retrieval-Augmented Generation (RAG) architecture: a knowledge graph-based retriever selects disease candidates from 1,058 conditions, and an LLM-based re-ranker applies prompt-based reasoning to refine predictions. Unlike traditional diagnostic models that require supervised training and large clinical datasets, GPT-RagAD is privacy-preserving, scalable, and language-agnostic. Extensive evaluations on three multilingual datasets (Chinese and English) show that GPT-RagAD achieves 40.6% Hit@1 and 56.7% NDCG@10 on the Symptom2Disease benchmark—substantially outperforming embedding-based and direct LLM baselines. Ablation and sensitivity analyses further validate its robustness. GPT-RagAD presents a practical, lightweight solution for clinical triage and pre-diagnosis support.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-liu26a, title = {{GPT}-{RagAD}: Two-layer Retrieval-Augmented Multilingual Diagnosis System}, author = {Liu, Xinyi and Sun, Dachun and Fung, Yi R. and Hakkani-T{\"u}r, Dilek and Abdelzaher, Tarek}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {152--166}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/liu26a/liu26a.pdf}, url = {https://proceedings.mlr.press/v297/liu26a.html}, abstract = {We introduce GPT-RagAD, a multilingual, zero-shot automated diagnosis system that achieves high accuracy without relying on real patient data. GPT-RagAD adopts a two-layer Retrieval-Augmented Generation (RAG) architecture: a knowledge graph-based retriever selects disease candidates from 1,058 conditions, and an LLM-based re-ranker applies prompt-based reasoning to refine predictions. Unlike traditional diagnostic models that require supervised training and large clinical datasets, GPT-RagAD is privacy-preserving, scalable, and language-agnostic. Extensive evaluations on three multilingual datasets (Chinese and English) show that GPT-RagAD achieves 40.6% Hit@1 and 56.7% NDCG@10 on the Symptom2Disease benchmark—substantially outperforming embedding-based and direct LLM baselines. Ablation and sensitivity analyses further validate its robustness. GPT-RagAD presents a practical, lightweight solution for clinical triage and pre-diagnosis support.} }
Endnote
%0 Conference Paper %T GPT-RagAD: Two-layer Retrieval-Augmented Multilingual Diagnosis System %A Xinyi Liu %A Dachun Sun %A Yi R. Fung %A Dilek Hakkani-Tür %A Tarek Abdelzaher %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-liu26a %I PMLR %P 152--166 %U https://proceedings.mlr.press/v297/liu26a.html %V 297 %X We introduce GPT-RagAD, a multilingual, zero-shot automated diagnosis system that achieves high accuracy without relying on real patient data. GPT-RagAD adopts a two-layer Retrieval-Augmented Generation (RAG) architecture: a knowledge graph-based retriever selects disease candidates from 1,058 conditions, and an LLM-based re-ranker applies prompt-based reasoning to refine predictions. Unlike traditional diagnostic models that require supervised training and large clinical datasets, GPT-RagAD is privacy-preserving, scalable, and language-agnostic. Extensive evaluations on three multilingual datasets (Chinese and English) show that GPT-RagAD achieves 40.6% Hit@1 and 56.7% NDCG@10 on the Symptom2Disease benchmark—substantially outperforming embedding-based and direct LLM baselines. Ablation and sensitivity analyses further validate its robustness. GPT-RagAD presents a practical, lightweight solution for clinical triage and pre-diagnosis support.
APA
Liu, X., Sun, D., Fung, Y.R., Hakkani-Tür, D. & Abdelzaher, T.. (2026). GPT-RagAD: Two-layer Retrieval-Augmented Multilingual Diagnosis System. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:152-166 Available from https://proceedings.mlr.press/v297/liu26a.html.

Related Material