# Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference

arXiv: https://arxiv.org/abs/2604.19566 · HTML: https://mlsanity.com/paper/2604.19566/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [MedSTS: A Resource for Clinical Semantic Textual Similarity](https://mlsanity.com/paper/1808.09397/) (2018)
- [Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks](https://mlsanity.com/paper/2311.00508/) (2023)
- [Efficient Text Encoders for Labor Market Analysis](https://mlsanity.com/paper/2505.24640/) (2025)
- [The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder](https://mlsanity.com/paper/2602.18487/) (2026)

## Built on by (most cited first, 2 of 2)

- [ClinicalEncoder26AM: A Multlilingual Diagnosable ColBERT Model; Evidences from the MultiClinNER Shared Task](https://mlsanity.com/paper/2605.28521/) (2026)
- [ClinicalAligner26AM: A Cross-Lingual Aligner for Dataset Translation; Evidences from the MultiClinCorpus Shared Task](https://mlsanity.com/paper/2606.08673/) (2026)

## Abstract (arXiv)

Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failures and curate the training evidence needed to correct them. Late-interaction models such as ColBERT provide a first solution thanks to the interpretable token-level interaction scores they expose between document and query tokens. Yet this interpretability is shallow: it explains a particular document--query pairwise score, but does not reveal whether the model has learned a clinical concept in a stable, reusable, and context-sensitive way across diverse expressions. As a result, these scores provide limited support for diagnosing misunderstandings, identifying irreasonably distant biomedical concepts, or deciding what additional data or feedback is needed to address this. In this short position paper, we propose Diagnosable ColBERT, a framework that aligns ColBERT token embeddings to a reference latent space grounded in clinical knowledge and expert-provided conceptual similarity constraints. This alignment turns document encodings into inspectable evidence of what the model appears to understand, enabling more direct error diagnosis and more principled data curation without relying on large batteries of diagnostic queries.