A Counterfactual Explanation Framework for Retrieval Models
For researchers and practitioners in information retrieval, this work fills a gap in explainability by focusing on non-relevance, but the approach is incremental.
The paper addresses the lack of explainability for why a document is not favored by a retrieval model, proposing a counterfactual framework to identify which terms, if added, would improve its ranking. Experiments demonstrate effectiveness across statistical (BM25) and deep learning models (DRMM, DSSM, ColBERT, MonoT5).
Explainability has become a crucial concern in today's world, aiming to enhance transparency in machine learning and deep learning models. Information retrieval is no exception to this trend. In existing literature on explainability of information retrieval, the emphasis has predominantly been on illustrating the concept of relevance concerning a retrieval model. The questions addressed include why a document is relevant to a query, why one document exhibits higher relevance than another, or why a specific set of documents is deemed relevant for a query. However, limited attention has been given to understanding why a particular document is not favored (e.g., not within top-K) with respect to a query and a retrieval model. In an effort to address this gap, our work focuses on the question of what terms need to be added within a document to improve its ranking. This, in turn, answers the question of which words in the document played a role in not being favored by a retrieval model for a particular query. We use a counterfactual framework to solve the above-mentioned research problem. % To the best of our knowledge, we mark the first attempt to tackle this specific counterfactual problem (i.e. examining the absence of which words can affect the ranking of a document). Our experiments show the effectiveness of our proposed approach in predicting counterfactuals for both statistical (e.g. BM25) and deep-learning-based models (e.g. DRMM, DSSM, ColBERT, MonoT5).