# A White Box Analysis of ColBERT

arXiv: https://arxiv.org/abs/2012.09650 · HTML: https://mlsanity.com/paper/2012.09650/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval](https://mlsanity.com/paper/2503.19009/) (2025)
- [Efficient Constant-Space Multi-Vector Retrieval](https://mlsanity.com/paper/2504.01818/) (2025)
- [Mitigating the Position Bias of Transformer Models in Passage Re-Ranking](https://mlsanity.com/paper/2101.06980/) (2021)
- [Match Your Words! A Study of Lexical Matching in Neural Information Retrieval](https://mlsanity.com/paper/2112.05662/) (2021)
- [Generative Retrieval as Multi-Vector Dense Retrieval](https://mlsanity.com/paper/2404.00684/) (2024)
- [Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25](https://mlsanity.com/paper/2502.04645/) (2025)
- [Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval](https://mlsanity.com/paper/2410.18527/) (2024)
- [Simple Projection Variants Improve ColBERT Performance](https://mlsanity.com/paper/2510.12327/) (2025)
- [The Role of Complex NLP in Transformers for Text Ranking?](https://mlsanity.com/paper/2207.02522/) (2022)
- [GEM: A Native Graph-based Index for Multi-Vector Retrieval](https://mlsanity.com/paper/2603.20336/) (2026)
- [How Different are Pre-trained Transformers for Text Ranking?](https://mlsanity.com/paper/2204.07233/) (2022)
- [Explainability of Text Processing and Retrieval Methods: A Survey](https://mlsanity.com/paper/2212.07126/) (2022)
- [ColBERTSaR: Sparsified ColBERT Index via Product Quantization](https://mlsanity.com/paper/2606.05568/) (2026)

## Abstract (arXiv)

Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood. Recent work has claimed that BERT does not satisfy the classical IR axioms. However, we propose to dissect the matching process of ColBERT, through the analysis of term importance and exact/soft matching patterns. Even if the traditional axioms are not formally verified, our analysis reveals that ColBERT: (i) is able to capture a notion of term importance; (ii) relies on exact matches for important terms.