Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition
This work addresses the problem of limited human annotations for biomedical researchers, though it is incremental in combining existing methods with new evaluation metrics.
This paper tackles the challenge of generalizing to unseen concepts in biomedical concept recognition by proposing an evaluation framework with novel metrics and an LLM-based auto-labeled data pipeline, showing that LLM-generated data improves generalization but cannot fully replace manual annotations.
Generalization to unseen concepts is a central challenge due to the scarcity of human annotations in Mention-agnostic Biomedical Concept Recognition (MA-BCR). This work makes two key contributions to systematically address this issue. First, we propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization. Second, we explore LLM-based Auto-Labeled Data (ALD) as a scalable resource, creating a task-specific pipeline for its generation. Our research unequivocally shows that while LLM-generated ALD cannot fully substitute for manual annotations, it is a valuable resource for improving generalization, successfully providing models with the broader coverage and structural knowledge needed to approach recognizing unseen concepts. Code and datasets are available at https://github.com/bio-ie-tool/hi-ald.