sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912438950035456 |
|---|---|
| author | Ahuja, Sanchit Tanmay, Kumar Chauhan, Hardik Hansrajbhai Patra, Barun Aggarwal, Kriti Del Corro, Luciano Mitra, Arindam Dhamecha, Tejas Indulal Awadallah, Ahmed Choudhary, Monojit Chaudhary, Vishrav Sitaram, Sunayana |
| author_facet | Ahuja, Sanchit Tanmay, Kumar Chauhan, Hardik Hansrajbhai Patra, Barun Aggarwal, Kriti Del Corro, Luciano Mitra, Arindam Dhamecha, Tejas Indulal Awadallah, Ahmed Choudhary, Monojit Chaudhary, Vishrav Sitaram, Sunayana |
| contents | Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by incorporating contextually relevant examples in each training sample. Our ablation study shows that our approach enhances the multilingual capabilities of Mistral-7B and Phi-3-Small improving performance by an average of 39.8% and 11.2%, respectively, across multilingual benchmarks in reasoning, question answering, reading comprehension, and machine translation. Moreover, sPhinX maintains strong performance on English LLM benchmarks while exhibiting minimal to no catastrophic forgetting, even when trained on 51 languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09879 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting Ahuja, Sanchit Tanmay, Kumar Chauhan, Hardik Hansrajbhai Patra, Barun Aggarwal, Kriti Del Corro, Luciano Mitra, Arindam Dhamecha, Tejas Indulal Awadallah, Ahmed Choudhary, Monojit Chaudhary, Vishrav Sitaram, Sunayana Computation and Language Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by incorporating contextually relevant examples in each training sample. Our ablation study shows that our approach enhances the multilingual capabilities of Mistral-7B and Phi-3-Small improving performance by an average of 39.8% and 11.2%, respectively, across multilingual benchmarks in reasoning, question answering, reading comprehension, and machine translation. Moreover, sPhinX maintains strong performance on English LLM benchmarks while exhibiting minimal to no catastrophic forgetting, even when trained on 51 languages. |
| title | sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.09879 |