CREDENCE: Counterfactual Explanations for Document Ranking
Joel Rorseth, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh, Srivastava, Jaroslaw Szlichta
TL;DR
CREDENCE is an interactive tool that generates counterfactual explanations for document ranking, helping users understand and analyze ranking models through perturbations of queries, documents, and other factors.
Contribution
It introduces a novel approach to explainability in information retrieval by providing counterfactual explanations tailored to ranking problems, including user-driven perturbations.
Findings
Enables understanding of ranking models through perturbations.
Supports user interaction for custom explanations.
Provides insights into query and document influence on rankings.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Text Analysis Techniques · Topic Modeling · Information Retrieval and Search Behavior
MethodsTest