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.

翻译：信息检索方法（如检索增强生成）是现代应用的基础，但通常缺乏统计保证。一致性预测通过检索保证包含相关信息集合来解决此问题，然而现有方法产生的集合规模较大，导致计算成本高且响应时间慢。本研究提出一种分数精炼方法，对检索分数应用简单的单调变换，从而在保持统计保证的同时显著缩小一致性集合规模。在多个BEIR基准测试上的实验验证了本方法在生成包含相关信息的紧凑集合方面的有效性。