CeQe：基于语义证据的词汇检索增强方法

AI 摘要

arXiv 上发布了一项名为 CeQe 的研究，提出交叉编码器查询扩展（CE-QE）方法，通过从语义检索结果中提取关键术语来增强 BM25 词汇检索，解决词汇鸿沟问题。在 BEIR 基准上，该方法显著提升了词汇召回率，其融合变体 SESF 在 Recall@100 和 nDCG@10 上分别优于现有方法，且无需修改 BM25 索引。

正文节选

Computer Science > Information Retrieval Title:CeQe: Grounding Lexical Retrieval in Semantic Evidence View PDF HTML (experimental) Abstract:Lexical retrieval (BM25) captures exact keyword matches and weights terms by corpus-wide significance, but it is blind to the semantic vocabulary gap: when a relevant document phrases an answer differently from the query, BM25 never retrieves it, and no amount of downstream reranking or fusion can recover a document that was never in the candidat

发布时间：2026-08-04 12:00

抓取时间：2026-08-04 12:57

来源机构：arXiv