通过分数精炼缩小可信检索集合，提升效率且不丢失可靠性
Streamlining Conformal Information Retrieval via Score Refinement
- 对检索分数施加单调变换，实现更紧凑的可信集合
- 在多个BEIR基准上显著缩小集合规模，同时保持统计保证
- 适合需要快速响应且需可靠检索结果的场景
信息检索（IR）方法如检索增强生成，在现代应用中至关重要，但通常缺乏统计保障。置信预测通过提供包含相关资讯的检索集来解决此问题，但现有方法产生的集合过大，导致计算成本高、响应慢。本文提出一种分数精炼方法，对检索分数施加简单的单调变换，显著缩小置信集合规模，同时维持其统计保障。在多个BEIR基准上的实验验证了该方法在生成紧凑且包含相关信息集合方面的有效性。
原文摘要 · Abstract (English)
Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information.
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。