通过文档引发的表征变化判断相关性，无需阈值调优即可高效过滤无关内容。
RSRank: Learning Relevance from Representational Shifts
- 利用查询在文档条件下的表征变化作为相关性信号
- 在多个数据集上优于当前最佳重排序模型
- 训练过程自动过滤无关内容，无需人工设定阈值
随着企业部署基于RAG的系统以提供基于事实的回答，重排序已成为最终筛选相关与无关文档的关键步骤。现有重排序器常依赖启发式阈值进行最优过滤。此外，当前最先进的相关性评分方法使用语言模型的logit信号，而该信号是为下一个词预测设计的，并非专用于评估相关性。为此，我们识别出一种原理清晰的相关性信号：当查询条件依赖于某文档时，其内部状态产生的表征变化（RS）。我们发现，候选文档引起的表征变化与理想文档集合引起的表征变化之间的对齐程度，能有效指示相关性。基于此，我们提出一种轻量级训练框架，学习将表征变化映射为校准后的相关性分数。该训练目标天然实现零阈值过滤，减少对启发式调参的依赖。在多个不同的检索数据集上，我们的方法均优于当前最优重排序模型。
原文摘要 · Abstract (English)
As enterprises deploy RAG-based systems to provide grounded responses to user queries, reranking has become a critical component for the final filtering step that separates relevant from distracting or irrelevant documents. Existing rerankers often rely on heuristic thresholds to achieve optimal filtering. Moreover, for relevance scoring, state-of-the-art methods use a language model's logit signals, which are designed for next-token prediction, not for assessing relevance. To address these limitations, we identify a principled signal for relevance: the representational shift (RS) induced in a query's internal state when conditioned on a document. We observe that the alignment between (a) RS induced by a candidate document and (b) RS induced by an oracle document-set provides a robust indicator of relevance. Building on this insight, we introduce a lightweight training framework that learns projections mapping RS to calibrated relevance scores. Our training objectives naturally filter irrelevant content at a zero threshold, reducing dependence on heuristic tuning. Across diverse retrieval datasets, our method delivers gains over SOTA rerankers.
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。