# CREDENCE: Counterfactual Explanations for Document Ranking

arXiv: https://arxiv.org/abs/2302.04983 · HTML: https://mlsanity.com/paper/2302.04983/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2023.

## Built on by (most cited first, 3 of 3)

- [RAGE Against the Machine: Retrieval-Augmented LLM Explanations](https://mlsanity.com/paper/2405.13000/) (2024)
- [Explaining Expert Search and Team Formation Systems with ExES](https://mlsanity.com/paper/2405.12881/) (2024)
- [TempPerturb-Eval: On the Joint Effects of Internal Temperature and External Perturbations in RAG Robustness](https://mlsanity.com/paper/2512.01183/) (2025)

## Abstract (arXiv)

Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers. Embracing the unique properties of the ranking problem, we present counterfactual explanations in terms of document perturbations, query perturbations, and even other documents. Additionally, users may build and test their own perturbations, and extract insights about their query, documents, and ranker.