Explainable Information Retrieval in the Audit Domain

TL;DR

This paper explores how explainable information retrieval can enhance transparency and trust in audit-related search tasks, addressing challenges unique to high-stakes domains like finance and medicine.

Contribution

It highlights the importance of XIR in auditing, discusses key challenges, and proposes future research directions for domain-specific explainability.

Findings

XIR can improve trust and transparency in audit tasks

Auditing presents unique challenges for XIR implementation

Future research is needed to tailor XIR for high-stakes domains

Abstract

Conversational agents such as Microsoft Copilot and Google Gemini assist users with complex search tasks but often generate misleading or fabricated references. This undermines trust, particularly in high-stakes domains such as medicine and finance. Explainable information retrieval (XIR) aims to address this by making search results more transparent and interpretable. While most XIR research is domain-agnostic, this paper focuses on auditing -- a critical yet underexplored area. We argue that XIR systems can support auditors in completing their complex task. We outline key challenges and future research directions to advance XIR in this domain.