复杂分块未必更好，选策略要权衡效果与系统开销。
When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
- 对比八种分块方法在大规模数据上的表现
- 昂贵方法常难持续提升效果，性能受模型和数据影响大
- 适合关注系统效率的研究者或工程部署者
密集检索通常在每个文档用单一嵌入表示的基准上评估，尽管真实系统中长文档需分块处理。此时分块策略不仅影响检索效果，还涉及索引吞吐、查询延迟和内存占用。以往比较多聚焦于检索性能，忽视了运行成本的权衡。本文在两个可扩展语料库上，使用三种嵌入模型和多种语料规模，评估八种代表性分块策略，同时测量检索有效性与系统级开销。结果表明，计算代价高的方法很少能稳定优于简单分块；最佳策略取决于嵌入模型、数据集、语料规模及目标评估指标。相似性能的方法在运行成本上差异显著，说明分块应作为多目标设计决策。
原文摘要 · Abstract (English)
Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In these settings, the chosen chunking method not only affects retrieval quality, but also indexing throughput, query latency, and memory usage. Prior comparisons of chunking strategies have mainly focused on retrieval performance, leaving operational trade-offs underexplored. To address these issues, we evaluate eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs. Our results show that computationally expensive methods rarely provide consistent gains over simpler chunking. Instead, the best performing strategy depends on the embedding model, dataset, corpus size, and target retrieval metric. Methods with similar performance can also differ substantially in operational cost, showing that chunking should be seen as a multi-objective design decision.
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。