Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913045698052096 |
|---|---|
| author | Zeng, Qingcheng Lu, Yuheng Zhou, Zeqi Qi, Heli Yu, Puxuan Zhao, Fuheng Yanaka, Hitomi Xuan, Weihao Yokoya, Naoto |
| author_facet | Zeng, Qingcheng Lu, Yuheng Zhou, Zeqi Qi, Heli Yu, Puxuan Zhao, Fuheng Yanaka, Hitomi Xuan, Weihao Yokoya, Naoto |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17632 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers Zeng, Qingcheng Lu, Yuheng Zhou, Zeqi Qi, Heli Yu, Puxuan Zhao, Fuheng Yanaka, Hitomi Xuan, Weihao Yokoya, Naoto Information Retrieval 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. |
| title | Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.17632 |