用共指链接增强段落检索，提升稠密检索器效果
CLAP: Coreference-Linked Augmentation for Passage Retrieval
- 将段落拆成连贯块，解决指代关系，生成局部伪查询
- 在跨域场景下提升nDCG@10达20.68%，优于传统方法
- 无需领域知识，适合低资源或未知领域的检索任务
基于大语言模型的段落扩展在提升第一阶段检索方面展现出潜力，但常因语义漂移及与预训练语义空间不一致，在稠密检索器上表现不佳。此外，通常只有部分段落内容与查询相关，其余内容引入噪声——这一问题在分块处理破坏共指连续性后更加严重。我们提出核心指代链接增强框架（CLAP），一种轻量级的基于LLM的扩展方法：将段落分割为连贯块，解析共指链，并生成与稠密检索器表示对齐的局部伪查询。通过融合全局主题信号与细粒度子主题信号，实现跨领域稳健性能。即使在检索器能力增强时，仍保持持续增益，使稠密检索器达到甚至超越第二阶段排序器（如BM25 + MonoT5-3B），nDCG@10最高提升20.68%。该改进在跨域场景尤为显著，而传统依赖领域知识的LLM扩展方法在此类场景中往往失效。CLAP采用逻辑驱动的流程，实现鲁棒且领域无关的泛化能力。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based passage expansion has shown promise for enhancing first-stage retrieval, but often underperforms with dense retrievers due to semantic drift and misalignment with their pretrained semantic space. Beyond this, only a portion of a passage is typically relevant to a query, while the rest introduces noise--an issue compounded by chunking techniques that break coreference continuity. We propose Coreference-Linked Augmentation for Passage Retrieval (CLAP), a lightweight LLM-based expansion framework that segments passages into coherent chunks, resolves coreference chains, and generates localized pseudo-queries aligned with dense retriever representations. A simple fusion of global topical signals and fine-grained subtopic signals achieves robust performance across domains. CLAP yields consistent gains even as retriever strength increases, enabling dense retrievers to match or surpass second-stage rankers such as BM25 + MonoT5-3B, with up to 20.68% absolute nDCG@10 improvement. These improvements are especially notable in out-of-domain settings, where conventional LLM-based expansion methods relying on domain knowledge often falter. CLAP instead adopts a logic-centric pipeline that enables robust, domain-agnostic generalization.
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。