tt501 at ArchEHR-QA 2026: Few-Shot Prompting with Retrieval-Augmented Generation for Grounded Clinical EHR Question Answering

Tai Tan Tran


Abstract
We present the ArchEHR-QA 2026 shared task system of team tt501, which addresses evidence identification (Subtask 2), answer generation (Subtask 3), and evidence alignment (Subtask 4) from electronic health record notes. Our approach relies entirely on prompt engineering with xAI’s Grok models, without any task-specific fine-tuning or external knowledge. For evidence identification we compare a hybrid BM25 plus large language model (LLM) reranker with a full-context chain-of-thought ensemble and refinement step, finding that full-note reasoning yields higher recall and F1. For answer generation we implement a retrieval-augmented generation pipeline that conditions on predicted evidence sentences and few-shot examples, improving lexical and semantic faithfulness over a zero-shot baseline. For evidence alignment we design a recall-oriented few-shot prompt enriched with explicit rationales that teach the model how to map each answer sentence back to its supporting note sentences. We report official shared task results and analyse the impact of these design choices across the three subtasks.
Anthology ID:
2026.cl4health-1.46
Volume:
Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Deepak Gupta, Paul Thompson, Sophia Ananiadou, Dina Demner-Fushman
Venues:
CL4Health | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
497–505
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cl4health-46
DOI:
10.63317/2tjqwa7c7nqf
Bibkey:
Cite (ACL):
Tai Tan Tran. 2026. tt501 at ArchEHR-QA 2026: Few-Shot Prompting with Retrieval-Augmented Generation for Grounded Clinical EHR Question Answering. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 497–505, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
tt501 at ArchEHR-QA 2026: Few-Shot Prompting with Retrieval-Augmented Generation for Grounded Clinical EHR Question Answering (Tran, CL4Health 2026)
Copy Citation: