用简单布尔查询让AI搜索代理在100次调用内达到0.6863的检索效果。
Boolean queries are all you need?
- 基于字符串匹配密度评分，无需监督学习或词频统计。
- 在MS MARCO数据集上达0.6863 NDCG@10，优于多种主流检索器。
- 适合对轻量级、无训练依赖检索方案感兴趣的开发者。
我们为基于大模型的搜索代理配备了布尔检索引擎，用于检索TREC 2024 RAG赛道使用的MS MARCO V2.1去重段落集合。在86个主题的标准子集上，每主题限定100次模型调用预算，该代理实现了0.6863的NDCG@10表现，高于许多密集型、稀疏型及学习型的首阶段检索器。排序仅依据文档中与查询匹配的子串密度，无需监督学习、全局统计或词权重。形式上，查询语言是正则语言的严格子集，文档得分基于匹配项的数量与长度。尽管结果具探索性（因测试集在模型训练时已公开），但表明简单模式匹配可能已足够支持智能体搜索。
原文摘要 · Abstract (English)
We equipped an LLM-based search agent with access to a Boolean retrieval engine to search the MS MARCO V2.1 deduped segment collection used by the TREC 2024 RAG track. Over a standard track subset of 86 topics, and operating under a budget of 100 model calls/topic, the agent achieved an NDCG@10 of 0.6863, which would place it above many dense, sparse, and learned-sparse first-stage retrievers. Ranking is based solely on the density of corpus substrings matching a query, with no requirement for supervised learning, global statistics, or term weights. Formally, the query language expresses a strict subset of the regular languages, with a document's score based on the number and length of matches it contains. Although the results are more exploratory than definitive, because they are based on a single test collection that was publicly available during model training, they suggest that simple pattern matching may be sufficient for agentic search.
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。