MasonNLP at MEDIQA-SYNUR 2026: Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction

A H M Rezaul Karim, Özlem Uzuner


Abstract
Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale remains challenging. Documentation burden is substantial, with prior studies showing clinicians spend large portions of their workday on documentation and related desk work rather than direct patient care. MEDIQA-SYNUR focuses on observation extraction from conversational nurse-patient transcripts, requiring systems to normalize these narratives into a predefined schema with value-type constraints. We propose a modular retrieval-augmented generation (RAG) pipeline that uses the training set as an exemplar corpus, combines schema-constrained prompting (full schema vs. pruned candidate schema), deterministic schema-based postprocessing, and a second-pass audit, with two LLM backbones: Llama-4-Scout-17B-16E-Instruct and GPT-5.2 with corresponding embedding models for RAG. Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.
Anthology ID:
2026.clinicalnlp-1.17
Volume:
Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Asma Ben Abacha, Steven Bethard, Danielle Bitterman, Tristan Naumann, Kirk Roberts
Venues:
ClinicalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
153–162
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-clinicalnlp-17
DOI:
10.63317/2xwjn5f2urna
Bibkey:
Cite (ACL):
A H M Rezaul Karim and Özlem Uzuner. 2026. MasonNLP at MEDIQA-SYNUR 2026: Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 153–162, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
MasonNLP at MEDIQA-SYNUR 2026: Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction (Karim & Uzuner, ClinicalNLP 2026)
Copy Citation: