Efficient Continual Pre-training for Building Domain Specific Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918279995457536 |
|---|---|
| author | Xie, Yong Aggarwal, Karan Ahmad, Aitzaz |
| author_facet | Xie, Yong Aggarwal, Karan Ahmad, Aitzaz |
| contents | Large language models (LLMs) have demonstrated remarkable open-domain capabilities. LLMs tailored for a domain are typically trained entirely on domain corpus to excel at handling domain-specific tasks. In this work, we explore an alternative strategy of continual pre-training as a means to develop domain-specific LLMs over an existing open-domain LLM. We introduce FinPythia-6.9B, developed through domain-adaptive continual pre-training on the financial domain. Continual pre-trained FinPythia showcases consistent improvements on financial tasks over the original foundational model. We further explore simple but effective data selection strategies for continual pre-training. Our data selection strategies outperform vanilla continual pre-training's performance with just 10% of corpus size and cost, without any degradation on open-domain standard tasks. Our work proposes an alternative solution to building domain-specific LLMs cost-effectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_08545 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Efficient Continual Pre-training for Building Domain Specific Large Language Models Xie, Yong Aggarwal, Karan Ahmad, Aitzaz Computation and Language Large language models (LLMs) have demonstrated remarkable open-domain capabilities. LLMs tailored for a domain are typically trained entirely on domain corpus to excel at handling domain-specific tasks. In this work, we explore an alternative strategy of continual pre-training as a means to develop domain-specific LLMs over an existing open-domain LLM. We introduce FinPythia-6.9B, developed through domain-adaptive continual pre-training on the financial domain. Continual pre-trained FinPythia showcases consistent improvements on financial tasks over the original foundational model. We further explore simple but effective data selection strategies for continual pre-training. Our data selection strategies outperform vanilla continual pre-training's performance with just 10% of corpus size and cost, without any degradation on open-domain standard tasks. Our work proposes an alternative solution to building domain-specific LLMs cost-effectively. |
| title | Efficient Continual Pre-training for Building Domain Specific Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.08545 |