根据查询复杂度动态调整检索数量，提升生成效率与精度。
ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion
- 用双分数融合判断是否保留检索块，无需额外计算。
- 在MS MARCO上减少35%检索块，MRR@10达0.401。
- 真实场景下召回率超97%，误检为零，适合高并发应用。
固定数量的检索会无视查询复杂度，对简单查询过度检索，对复合查询则检索不足。本文提出ScoreGate，一种轻量级的分数空间决策机制，在推理时基于双编码器相似度s_i和交叉编码器重排序分r_i动态控制检索数量，无需额外模型推断。其核心思想是：交叉编码器可挽救因词汇不匹配被双编码器低估的相关块——这是固定K或单分数阈值无法解决的问题。在MS MARCO（200个开发集查询）上，ScoreGate以35%更少的保留块实现MRR@10 = 0.401；在内部基准测试（n=300，Fleiss' kappa=0.87）中，召回率达97.77%-99.34%且零误报（95%置信区间[96.4%, 100%]），每查询减少34.8%的词元数，仅增加31ms延迟。多数据集与生产流量结果表明，自适应检索数量可在不降低质量的前提下提升效率。
原文摘要 · Abstract (English)
Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch -- a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.
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。