Explainable Information Retrieval

Avishek Anand, Sourav Saha, Venktesh V

Abstract: This tutorial presents explainability of retrieval methods, an emerging area focused on fostering responsible and trustworthy deployment of machine learning systems in the context of information retrieval. As the field has rapidly evolved in the past 4–5 years, numerous approaches have been proposed that focus on different access modes, stakeholders, and model development stages. This tutorial aims to introduce IR-centric notions, classification, and evaluation styles in explainable information retrieval (ExIR) while focusing on IR-specific tasks such as ranking, text classification, and learning-to-rank systems. We will extensively cover post-hoc methods, probing approaches, and recent advances in interpretability-by-design approaches. We will also discuss ExIR applications for different stakeholders, such as researchers, practitioners, and end-users, in contexts like web search, legal search, and high-stakes decision-making tasks. To facilitate practical understanding, we will provide a hands-on session on ExIR methods, reducing the entry barrier for students, researchers, and practitioners alike. Earlier version of this tutorial has been presented in SIGIR 2023 and FIRE 2023.