XViewRank：面向大语言模型增强稀疏检索的重叠条件分数融合方法
XViewRank: Overlap-Conditioned Score Fusion for LLM-Augmented Sparse Retrieval
AI总结：
本研究针对LLM增强稀疏检索的固定融合缺陷，提出XViewRank方法，通过重叠条件融合BM25分数，在TREC DL数据集上较倒数排名融合取得更优检索效果。
摘要：
大语言模型可通过生成查询的替代视图减少稀疏检索中的词汇不匹配问题，但这些视图独立检索后，其排名列表可能存在互补、冗余或受查询漂移影响的情况，使得固定融合方法效果欠佳。本文提出XViewRank，一种轻量级检索端方法，用于条件性融合原始查询、假设视图及退阶视图的BM25结果。对于每个池化候选，XViewRank保留三个归一化BM25分数，以及检索结果集之间的三个查询级重叠值；一个小型非线性评分器将这些重叠值作为上下文，用于调整视图特定分数的解释方式，无需联合编码查询与段落文本。在匹配输入协议下，XViewRank在TREC DL 2019和2020数据集上的nDCG@10和MAP指标数值上优于倒数排名融合，其中在DL19上的MAP提升具有统计显著性。额外分析显示，当视图排名一致性较低时，XViewRank的优势最为明显，而在DL20上的证据较弱。这些结果表明，重叠条件分数融合可作为固定融合的紧凑检索端替代方案，同时明确了其经验优势的适用范围。
英文摘要：
Large language models can reduce vocabulary mismatch in sparse retrieval by generating alternative views of a query. Once these views are searched independently, however, their ranked lists may be complementary, redundant, or affected by query drift, making fixed fusion suboptimal. We present XViewRank, a lightweight retrieval-side method for conditionally fusing BM25 results from an original query, a hypothesis view, and a step-back view. For each pooled candidate, XViewRank retains three normalized BM25 scores and three query-level overlaps between the retrieved result sets. A small nonlinear scorer uses the overlaps as context that changes how the view-specific scores are interpreted, without jointly encoding query and passage text. Under a matched-input protocol, XViewRank improves nDCG@10 and MAP numerically over reciprocal rank fusion on both TREC DL 2019 and 2020, with a statistically significant MAP gain on DL19. Additional analyses show that the clearest benefit occurs when the view rankings have low agreement, while the evidence on DL20 is weaker. The results support overlap-conditioned score fusion as a compact retrieval-side alternative to fixed fusion, while also delimiting where its advantage is empirically established.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
