LTRC-IIIT at MEDIQA-SYNUR 2026: Benchmarking a Fully Local, Training-Free RAG Pipeline

Aashwin Vaish, Dipti Misra Sharma


Abstract
In this paper we present our solution to MEDIQA-SYNUR 2026 shared task organized at LREC-ClinicalNLP workshop. The goal of the task is to populate Electronic Health Record (EHR) flowsheets using the transcriptions of nurse dictations, to alleviate the extensive manual labor associated with sifting through large flowsheets of clinical concepts. We propose a modular architecture combining heuristic-driven Retrieval-Augmented Generation (RAG) with grammar-constrained decoding on an open-weight, quantized, 8B-parameter model (Llama 3.1 Instruct). Our system achieves an F1 score of 0.57, significantly trailing the initial zero-shot experiments with GPT-4o and placing it towards the lower end of the current leaderboard. We conduct a failure analysis of this approach while establishing a baseline for privacy-preserving, zero-shot documentation assistants.
Anthology ID:
2026.clinicalnlp-1.15
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:
136–140
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-clinicalnlp-15
DOI:
10.63317/3wbuccufqusz
Bibkey:
Cite (ACL):
Aashwin Vaish and Dipti Misra Sharma. 2026. LTRC-IIIT at MEDIQA-SYNUR 2026: Benchmarking a Fully Local, Training-Free RAG Pipeline. In Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026, pages 136–140, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
LTRC-IIIT at MEDIQA-SYNUR 2026: Benchmarking a Fully Local, Training-Free RAG Pipeline (Vaish & Sharma, ClinicalNLP 2026)
Copy Citation: