Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism

Hippolyte Gisserot-Boukhlef,Manuel Faysse, Emmanuel Malherbe, Céline Hudelot,Pierre Colombo

CoRR(2024)

引用 0|浏览0
暂无评分
摘要
Neural Information Retrieval (NIR) has significantly improved upon heuristic-based IR systems. Yet, failures remain frequent, the models used often being unable to retrieve documents relevant to the user's query. We address this challenge by proposing a lightweight abstention mechanism tailored for real-world constraints, with particular emphasis placed on the reranking phase. We introduce a protocol for evaluating abstention strategies in a black-box scenario, demonstrating their efficacy, and propose a simple yet effective data-driven mechanism. We provide open-source code for experiment replication and abstention implementation, fostering wider adoption and application in diverse contexts.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要