MindMerger: Efficient Boosting LLM Reasoning in non-English Languages
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909211428913152 |
|---|---|
| author | Huang, Zixian Zhu, Wenhao Cheng, Gong Li, Lei Yuan, Fei |
| author_facet | Huang, Zixian Zhu, Wenhao Cheng, Gong Li, Lei Yuan, Fei |
| contents | Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English languages, while others replace non-English inputs with an external model's outputs such as English translation text to circumvent the challenge of LLM understanding non-English. Unfortunately, these methods often underutilize the built-in skilled reasoning and useful language understanding capabilities of LLMs. In order to better utilize the minds of reasoning and language understanding in LLMs, we propose a new method, namely MindMerger, which merges LLMs with the external language understanding capabilities from multilingual models to boost the multilingual reasoning performance. Furthermore, a two-step training scheme is introduced to first train to embeded the external capabilities into LLMs and then train the collaborative utilization of the external capabilities and the built-in capabilities in LLMs. Experiments on three multilingual reasoning datasets and a language understanding dataset demonstrate that MindMerger consistently outperforms all baselines, especially in low-resource languages. Without updating the parameters of LLMs, the average accuracy improved by 6.7% and 8.0% across all languages and low-resource languages on the MGSM dataset, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17386 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MindMerger: Efficient Boosting LLM Reasoning in non-English Languages Huang, Zixian Zhu, Wenhao Cheng, Gong Li, Lei Yuan, Fei Computation and Language Artificial Intelligence Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English languages, while others replace non-English inputs with an external model's outputs such as English translation text to circumvent the challenge of LLM understanding non-English. Unfortunately, these methods often underutilize the built-in skilled reasoning and useful language understanding capabilities of LLMs. In order to better utilize the minds of reasoning and language understanding in LLMs, we propose a new method, namely MindMerger, which merges LLMs with the external language understanding capabilities from multilingual models to boost the multilingual reasoning performance. Furthermore, a two-step training scheme is introduced to first train to embeded the external capabilities into LLMs and then train the collaborative utilization of the external capabilities and the built-in capabilities in LLMs. Experiments on three multilingual reasoning datasets and a language understanding dataset demonstrate that MindMerger consistently outperforms all baselines, especially in low-resource languages. Without updating the parameters of LLMs, the average accuracy improved by 6.7% and 8.0% across all languages and low-resource languages on the MGSM dataset, respectively. |
| title | MindMerger: Efficient Boosting LLM Reasoning in non-English Languages |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.17386 |