CREDENCE: Counterfactual Explanations for Document Ranking

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.

Accepted by ICDE 2023 (Demonstration Track)

References in corpus (3)

• Distributed Representations of Sentences and Documents
• A study on the Interpretability of Neural Retrieval Models using DeepSHAP
• Helping results assessment by adding explainable elements to the deep relevance matching model

Cited by in corpus (1)

• RAGE Against the Machine: Retrieval-Augmented LLM Explanations