CREDENCE: Counterfactual Explanations for Document Ranking
About
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.
Joel Rorseth, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh Srivastava, Jaroslaw Szlichta• 2023
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Counterfactual Explanation for Information Retrieval | MS MARCO Passage | Fidelity (%)75 | 6 | |
| Counterfactual Explanation for Information Retrieval | MS MARCO Document | FD (%)70 | 6 | |
| Counterfactual Explanation for Information Retrieval | TREC Robust | Fidelity (FD)72 | 6 |
Showing 3 of 3 rows