# Extractive Explanations for Interpretable Text Ranking

arXiv: https://arxiv.org/abs/2106.12460 · HTML: https://mlsanity.com/paper/2106.12460/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2021.

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Context Aware Query Rewriting for Text Rankers using LLM](https://mlsanity.com/paper/2308.16753/) (2023)
- [Query Understanding in the Age of Large Language Models](https://mlsanity.com/paper/2306.16004/) (2023)
- [Explaining Search Result Stances to Opinionated People](https://mlsanity.com/paper/2309.08460/) (2023)
- [Can LLMs extract human-like fine-grained evidence for evidence-based fact-checking?](https://mlsanity.com/paper/2511.21401/) (2025)
- [Explainability of Text Processing and Retrieval Methods: A Survey](https://mlsanity.com/paper/2212.07126/) (2022)
- [The Surprising Effectiveness of Rankers Trained on Expanded Queries](https://mlsanity.com/paper/2404.02587/) (2024)
- [CREST: Improving Interpretability and Effectiveness of Troubleshooting at Ericsson through Criterion-Specific Trouble Report Retrieval](https://mlsanity.com/paper/2511.17417/) (2025)
- [The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search](https://mlsanity.com/paper/2608.23252/) (2026)

## Abstract (arXiv)

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents. In this paper we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-and-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-to-end training technique for Select-and-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick. We conduct extensive experiments to demonstrate that our approach is competitive to state-of-the-art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design. Finally, we present real-world applications that benefit from our sentence selection method.