QIME: Constructing Interpretable Medical Text Embeddings via Ontology-Grounded Questions

TL;DR

QIME is a novel ontology-grounded framework that creates interpretable, clinically meaningful biomedical text embeddings by using question-based dimensions, improving transparency and performance over prior methods.

Contribution

QIME introduces a training-free, ontology-grounded approach for constructing interpretable medical embeddings with semantically atomic questions, enhancing interpretability and effectiveness.

Findings

Outperforms prior interpretable embedding methods in biomedical tasks

Narrower performance gap to black-box biomedical encoders

Provides concise, clinically informative explanations

Abstract

While dense biomedical embeddings achieve strong performance, their black-box nature limits their utility in clinical decision-making. Recent question-based interpretable embeddings represent text as binary answers to natural-language questions, but these approaches often rely on heuristic or surface-level contrastive signals and overlook specialized domain knowledge. We propose QIME, an ontology-grounded framework for constructing interpretable medical text embeddings in which each dimension corresponds to a clinically meaningful yes/no question. By conditioning on cluster-specific medical concept signatures, QIME generates semantically atomic questions that capture fine-grained distinctions in biomedical text. Furthermore, QIME supports a training-free embedding construction strategy that eliminates per-question classifier training while further improving performance. Experiments across biomedical semantic similarity, clustering, and retrieval benchmarks show that QIME consistently outperforms prior interpretable embedding methods and substantially narrows the gap to strong black-box biomedical encoders, while providing concise and clinically informative explanations.