用列表重排日志隐式构建文档图，实现高效无额外调用的检索优化
On Listwise Reranking for Corpus Feedback
- 从列表重排日志中隐式生成文档相似性图，避免显式计算开销
- 在TREC-DL和BEIR数据集上达到与理想图方法相当的检索效果
- 无需额外大模型调用，适合对推理效率敏感的生产系统
重排器通过捕捉文档间交互关系提升检索性能。在极端情况下，图感知自适应检索（GAR）采用信息丰富的图结构，但需预先计算文档相似性图，而此类图通常不可用或带来二次方内存开销。为此，无图重排器借助大语言模型（LLM）调用实现良好表现。本文提出L2G框架，通过将列表重排日志中的信号转化为图结构，隐式构建文档图，从而实现无需显式图计算的可扩展图基检索。在TREC-DL和BEIR子集上的实验表明，L2G在不增加任何额外LLM调用的前提下，达到了基于理想图方法的性能水平。
原文摘要 · Abstract (English)
Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a pre-computed document similarity graph in reranking. However, as such graphs are often unavailable, or incur quadratic memory costs even when available, graph-free rerankers leverage large language model (LLM) calls to achieve competitive performance. We introduce L2G, a novel framework that implicitly induces document graphs from listwise reranker logs. By converting reranker signals into a graph structure, L2G enables scalable graph-based retrieval without the overhead of explicit graph computation. Results on the TREC-DL and BEIR subset show that L2G matches the effectiveness of oracle-based graph methods, while incurring zero additional LLM calls.
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。