# Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation

arXiv: https://arxiv.org/abs/2304.12631 · HTML: https://mlsanity.com/paper/2304.12631/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models](https://mlsanity.com/paper/2101.05667/) (2021)
- [TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime](https://mlsanity.com/paper/2104.09399/) (2021)
- [A study on the Interpretability of Neural Retrieval Models using DeepSHAP](https://mlsanity.com/paper/1907.06484/) (2019)
- [Explainable Information Retrieval: A Survey](https://mlsanity.com/paper/2211.02405/) (2022)
- [To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers](https://mlsanity.com/paper/2205.00235/) (2022)
- [Towards Axiomatic Explanations for Neural Ranking Models](https://mlsanity.com/paper/2106.08019/) (2021)
- [Interpreting Neural Ranking Models using Grad-CAM](https://mlsanity.com/paper/2005.05768/) (2020)
- [Explaining Documents' Relevance to Search Queries](https://mlsanity.com/paper/2111.01314/) (2021)
- [Helping results assessment by adding explainable elements to the deep relevance matching model](https://mlsanity.com/paper/2106.05147/) (2021)

## Built on by (most cited first, 5 of 5)

- [Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community](https://mlsanity.com/paper/2307.09751/) (2023)
- [Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval](https://mlsanity.com/paper/2506.00041/) (2025)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation](https://mlsanity.com/paper/2505.08450/) (2025)
- [IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation](https://mlsanity.com/paper/2601.20084/) (2026)

## Abstract (arXiv)

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations. These models, however, suffer from poor interpretability as they do not rely on explicit term matching. As a form of local per-query explanations, we introduce the notion of equivalent queries that are generated by maximizing the similarity between the NRM's results and the result set of a sparse retrieval system with the equivalent query. We then compare this approach with existing methods such as RM3-based query expansion and contrast differences in retrieval effectiveness and in the terms generated by each approach.