EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911729896652800 |
|---|---|
| author | Koo, Hamin Kim, Jaehyung |
| author_facet | Koo, Hamin Kim, Jaehyung |
| contents | Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing multilingual prompting methods emphasize reformulating queries into English or enhancing reasoning capabilities, they often fail to incorporate the language- and culture-specific grounding that is essential for some queries. To address this limitation, we propose EMCEE (Extracting synthetic Multilingual Context and merging), a simple yet effective framework that enhances the multilingual capabilities of LLMs by explicitly extracting and utilizing query-relevant knowledge from the LLM itself. In particular, EMCEE first extracts synthetic context to uncover latent, language-specific knowledge encoded within the LLM, and then dynamically merges this contextual insight with reasoning-oriented outputs through a judgment-based selection mechanism. Extensive experiments on four multilingual benchmarks covering diverse languages and tasks demonstrate that EMCEE consistently outperforms prior approaches, achieving an average relative improvement of 16.4% overall and 31.7% in low-resource languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context Koo, Hamin Kim, Jaehyung Computation and Language Artificial Intelligence Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing multilingual prompting methods emphasize reformulating queries into English or enhancing reasoning capabilities, they often fail to incorporate the language- and culture-specific grounding that is essential for some queries. To address this limitation, we propose EMCEE (Extracting synthetic Multilingual Context and merging), a simple yet effective framework that enhances the multilingual capabilities of LLMs by explicitly extracting and utilizing query-relevant knowledge from the LLM itself. In particular, EMCEE first extracts synthetic context to uncover latent, language-specific knowledge encoded within the LLM, and then dynamically merges this contextual insight with reasoning-oriented outputs through a judgment-based selection mechanism. Extensive experiments on four multilingual benchmarks covering diverse languages and tasks demonstrate that EMCEE consistently outperforms prior approaches, achieving an average relative improvement of 16.4% overall and 31.7% in low-resource languages. |
| title | EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.05846 |