Query-based Model Collaboration Enables Expert-level Clinical Text Augmentation

Dongkyu Cho, Miao Zhang, Gregory D Lyng, Rumi Chunara

Keywords: Data augmentation, Large language models, Healthcare

TL;DR: We propose a safer data augmentation method that integrates expert-level clinical knowledge using model collaboration.

Abstract: Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples. While large language models (LLMs) have demonstrated strong generative capabilities for this purpose, their applications in high-stakes domains like healthcare present unique challenges due to the risk of generating clinically incorrect or misleading information. In this work, we propose a novel query-based model collaboration framework that integrates expert-level domain knowledge to guide the augmentation process to preserve critical medical information. Compared to existing LLM-based and traditional augmentation methods, our generated data significantly improves preservation of critical medical information and reduces hallucinations at both the token and concept levels. Experiments on downstream clinical prediction tasks demonstrate consistent performance gains over existing augmentation methods. This lightweight collaborative framework addresses the gap between LLM augmentation potential and the safety requirements of specialized domains.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 77