对比25种分块策略，发现递归分块+专用嵌入模型最高效。
Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation
- 采用递归令牌分块（R100-0）和检索优化嵌入模型。
- 在3个化学基准上表现最优，资源开销低。
- 适合构建高效化学信息检索生成系统。
检索增强生成（RAG）系统在应对不断增长的科学文献方面日益重要，尤其在高风险领域如化学中。尽管RAG前景广阔，但其基础设计选择——如文档分块与表示方式——在特定领域仍缺乏深入研究。本研究首次对面向化学的RAG系统中的分块策略与嵌入模型进行大规模系统评估。我们考察了五类方法下的25种分块配置，并在三个化学专用基准上评估了48种嵌入模型，其中包括新提出的QuestChemRetrieval数据集。结果表明，递归令牌分块（特别是R100-0）始终优于其他方法，在资源开销极小的情况下实现优异性能。同时，检索优化型嵌入（如Nomic和Intfloat E5变体）显著优于领域专用模型（如SciBERT）。通过公开数据集、评估框架与实证基准，本研究为构建高效、有效的化学感知RAG系统提供了可操作的指导。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design choices -- such as how documents are segmented and represented -- remain underexplored in domain-specific contexts. This study presents the first large-scale, systematic evaluation of chunking strategies and embedding models tailored to chemistry-focused RAG systems. We investigate 25 chunking configurations across five method families and evaluate 48 embedding models on three chemistry-specific benchmarks, including the newly introduced QuestChemRetrieval dataset. Our results reveal that recursive token-based chunking (specifically R100-0) consistently outperforms other approaches, offering strong performance with minimal resource overhead. We also find that retrieval-optimized embeddings -- such as Nomic and Intfloat E5 variants -- substantially outperform domain-specialized models like SciBERT. By releasing our datasets, evaluation framework, and empirical benchmarks, we provide actionable guidelines for building effective and efficient chemistry-aware RAG systems.
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。