让审计搜索结果可解释，提升关键领域信任度
Explainable Information Retrieval in the Audit Domain
- 设计面向审计场景的可解释检索框架
- 解决对话系统生成虚假引用的问题
- 适合审计、金融等高风险领域研究者
微软Copilot和谷歌Gemini等对话式代理在处理复杂搜索任务时，常产生误导性或虚构的参考文献，损害用户信任，尤其在医疗、金融等高风险领域问题突出。可解释信息检索（XIR）旨在提升搜索结果的透明度与可理解性。尽管多数XIR研究为通用领域，本文聚焦审计这一重要但研究不足的领域，论证XIR系统可辅助审计人员完成复杂任务，并提出该领域关键挑战与未来研究方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。