QIME: Constructing Interpretable Medical Text Embeddings via Ontology-Grounded Questions
This addresses the need for interpretable embeddings in clinical decision-making, offering a domain-specific incremental improvement.
The paper tackled the problem of black-box biomedical embeddings by proposing QIME, an ontology-grounded framework that constructs interpretable medical text embeddings as binary answers to clinically meaningful questions, achieving consistent performance gains over prior interpretable methods and narrowing the gap to black-box encoders.
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.