cs.CLNov 4, 2026

Interpretable Text Embeddings Based on Hierarchical Questions

Authors: Kohei Oda, Po-Min Chuang, Kiyoaki Shirai, Natthawut Kertkeidkachorn

Organizations: Japan Advanced Institute of Science and Technology · Independent Researcher

Abstract

QA-based text embeddings represent texts as vectors consisting of 1/0 answers to yes/no questions. Although these embeddings provide detailed information for interpretation and achieve high task performance, they often require humans to examine a large number of questions. Furthermore, the relationship between the number of questions and the appropriate level of question granularity has not been sufficiently studied. To address these challenges, we propose a method for constructing hierarchical questions for text embeddings. As the hierarchy deepens, questions become more specific and their number increases. During interpretation, we reduce the number of questions that humans need to examine by replacing questions at deeper levels with aligned questions at shallower levels. The question hierarchy is constructed through recursive clustering, contrastive prompting, and question alignment. Experimental results on general-purpose tasks show that our method improves interpretability while maintaining task performance. It is also found that, when only a limited number of questions are available, questions at shallower levels tend to achieve higher task performance than those at deeper levels, even with the same number of questions.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text

    Mar 2, 2026Yixuan Tang, Zhenghong Lin, Yandong Sun +3Text EmbeddingsRepresentation Learning

  2. Balancing hierarchical representation and quantization: A performance trade-off in text embeddings

    Nov 4, 2026Kai Ponel, Marco Polignano, Erasmo Purificato +4Embedding CompressionText Embedding Evaluation

  3. Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering

    May 26, 2026Lukas Ellinger, Alexander Fichtl, Miriam Anschütz +1Question Answering