研究混合语言查询检索，发现现有系统在跨语言切换时表现大幅下降。
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
- 构建人工标注的混合语言检索数据集CSR-L，真实还原语言混用场景。
- 多模型评估显示，跨语言切换使检索性能最高下降27%。
- 现有多语言技术无法完全解决此问题，揭示当前系统脆弱性。
代码切换是全球交流中普遍存在的语言现象，但现代信息检索系统仍主要针对单语环境设计与评估。为弥合这一关键差距，我们开展了一项全面的代码切换信息检索研究。提出CSR-L（代码切换检索基准-精简版），通过人工标注构建数据集，以捕捉混合语言查询的真实自然性。在统计、密集和晚期交互范式下的评估表明，代码切换构成根本性性能瓶颈，即使强大的多语言模型也显著退化。我们证明，这种失败源于纯语言与混合语言文本在嵌入空间中的显著差异。进一步扩展研究，提出CS-MTEB，涵盖11种多样化任务，观察到性能最高下降27%。最后，我们表明标准多语言技术如词汇扩展无法完全弥补这些缺陷。这些发现突显了当前系统的脆弱性，并确立代码切换为未来信息检索优化的关键前沿。
原文摘要 · Abstract (English)
Code-switching is a pervasive linguistic phenomenon in global communication, yet modern information retrieval systems remain predominantly designed for, and evaluated within, monolingual contexts. To bridge this critical disconnect, we present a holistic study dedicated to code-switching IR. We introduce CSR-L (Code-Switching Retrieval benchmark-Lite), constructing a dataset via human annotation to capture the authentic naturalness of mixed-language queries. Our evaluation across statistical, dense, and late-interaction paradigms reveals that code-switching acts as a fundamental performance bottleneck, degrading the effectiveness of even robust multilingual models. We demonstrate that this failure stems from substantial divergence in the embedding space between pure and code-switched text. Scaling this investigation, we propose CS-MTEB, a comprehensive benchmark covering 11 diverse tasks, where we observe performance declines of up to 27%. Finally, we show that standard multilingual techniques like vocabulary expansion are insufficient to resolve these deficits completely. These findings underscore the fragility of current systems and establish code-switching as a crucial frontier for future IR optimization.
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。