Aurum at CRF Filling 2026: Modular DSPy Extractors with Qwen3-Max for Multilingual CRF Filling

Vinay Babu Ulli, Jyoti Kumari, Anindita Mondal


Abstract
This paper describes the submission by Team Aurum to the CL4Health @ LREC 2026 Shared Task on Case Report Form (CRF) Filling from dyspnea patient clinical notes. Extracting 134 structured clinical fields using a single Large Language Model (LLM) call often leads to schema-following errors, hallucination, and poor attention over complex instructions. To address this, we propose a modular extraction pipeline built with DSPy, which decomposes the 134 CRF fields into 14 specialized, domain-specific extractors (e.g., Medical History, Lab Values, Acute Diagnoses). We conducted extensive experiments across multiple multilingual LLMs, including Llama4 Maverik, GPT-4o, GPT-4o Mini, DeepSeek-V3, Gemma-3-12B-Instruct, and Qwen-series models. Among these, Qwen3-Max (Thinking) with our optimized v2 prompts achieved the best performance on the development set with a Macro-F1 of 0.70, outperforming other evaluated models such as GPT-4o (0.68) and DeepSeek-V3 (0.66). Prompt optimization resulted in measurable gains, improving Qwen3-Max performance from 0.67 to 0.70. Using this configuration, our pipeline achieved an official Codabench Test Macro-F1 score of 0.68 in English and 0.67 in Italian, securing the 1st place ranking overall in the shared task.
Anthology ID:
2026.cl4health-1.36
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:
395–401
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cl4health-36
DOI:
10.63317/4h5ugiqk5eht
Bibkey:
Cite (ACL):
Vinay Babu Ulli, Jyoti Kumari, and Anindita Mondal. 2026. Aurum at CRF Filling 2026: Modular DSPy Extractors with Qwen3-Max for Multilingual CRF Filling. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 395–401, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Aurum at CRF Filling 2026: Modular DSPy Extractors with Qwen3-Max for Multilingual CRF Filling (Ulli et al., CL4Health 2026)
Copy Citation: