Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition

TL;DR

This paper introduces an evaluation framework and an LLM-based auto-labeling pipeline to enhance the generalization of biomedical concept recognition models to unseen concepts, addressing annotation scarcity.

Contribution

It presents a novel evaluation framework and a scalable LLM-based auto-labeling pipeline to improve model generalization in biomedical concept recognition.

Findings

LLM-generated auto-labeled data improves model coverage

The framework effectively measures generalization to unseen concepts

Auto-labeled data complements manual annotations

Abstract

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.