Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Code-Switching In-Context Learning for Cross-Lingual Transfer of Large Language Models

Domain:

natural language processing

Record type:

paper
Creator:
YooJinChoOh,
Host:avatar
While large language models (LLMs) exhibit strong multilingual abilities, their reliance on English as latent representations creates a translation barrier, where reasoning implicitly depends on internal translation into English. When this process fails, performance in non-English languages deteriorates sharply, limiting the inclusiveness of LLM-based applications. Existing cross-lingual in-context learning (X-ICL) methods primarily leverage monolingual demonstrations, often failing to mitigate this barrier and instead reinforcing it. In this work, we introduce code-switching in-context learning (CSICL), a simple yet effective prompting strategy that progressively transitions from a target language to English within demonstrations and instruction to facilitate their latent reasoning in English. By explicitly scaffolding the reasoning process through controlled code-switching, CSICL acts as an implicit linguistic bridge that enhances cross-lingual alignment and reduces reliance on the translation barrier. We conduct extensive experiments across 4 LLMs, 6 datasets, and 10 languages, spanning both knowledge-intensive and reasoning-oriented domains. Our results demonstrate that CSICL consistently outperforms X-ICL baselines, achieving gains of 3.1%p and 1.9%p in both target and unseen languages, respectively. The improvement is even more pronounced in low-resource settings, with gains of 14.7% in target and 5.3% in unseen languages. These findings establish code-switching as a principled and robust approach for overcoming the translation barrier during inference, moving LLMs toward more equitable and effective multilingual systems.

Visit

arxiv.org

Tasks

code switchingtransfer learning

Tags

Computation and LanguageArtificial Intelligence

Similar

BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual TransferEffects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language ModelsFew-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource LanguagesArtificial Code-Switching Effects on Zero-Shot Transfer in Cross-Lingual RetrievalContrastive Cross-Lingual Calibration for Large Language ModelsLeft Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer

Despite remarkable advancements in few-shot generalization in natural language processing, most mode

Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models

Character-based Neural Network Language Models (NNLM) have the advantage of smaller vocabulary and t

Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages

Large pre-trained language models (PLMs) are at the forefront of advances in Natural Language Proces

Artificial Code-Switching Effects on Zero-Shot Transfer in Cross-Lingual Retrieval

Transferring information retrieval (IR) models from a high-resource language (typically English) to

Contrastive Cross-Lingual Calibration for Large Language Models

Large language models (LLMs) are increasingly deployed in multilingual settings, yet their probabili

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

We investigate how large language models perform on low-resource languages by benchmarking eight LLM