paper-with-me

Papers

Efficient Continual Pre-training for Building Domain Specific Large Language Models

2023-11-14 · Yong Xie, Karan Aggarwal, Aitzaz Ahmad

Large language models (LLMs) have demonstrated remarkable open-domain capabilities. Traditionally, LLMs tailored for a domain are trained from scratch 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. 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 outperforms 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 from scratch in a cost-effective manner.

📄 PDF Abstract BibTeX arXiv:2311.08545

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model

2022-11-21 · Yongyu Yan, Kui Xue, Xiaoming Shi, Qi Ye 외

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forget…

Continual PretrainingLanguage ModelingLanguage Modelling

EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data

2023-12-25 · Shirong Ma, Shen Huang, Shulin Huang, Xiaobin Wang 외

Large Language Models (LLMs) pre-trained on massive corpora have exhibited remarkable performance on various NLP tasks. However, applying these models to specific domains still poses significant challenges, such as lack …

In-Context Learning

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

2024-06-24 · Tong Zhu, Xiaoye Qu, Daize Dong, Jiacheng Ruan 외

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry a…

Mixture-of-Experts

AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy

2024-09-29 · Rui Pan, Tuan Dung Nguyen, Hardik Arora, Alberto Accomazzi 외

Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objecti…

AstronomyBenchmarkingContinual Pretraining

Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training

2024-04-16 · Masanori Hirano, Kentaro Imajo

Large language models (LLMs) are now widely used in various fields, including finance. However, Japanese financial-specific LLMs have not been proposed yet. Hence, this study aims to construct a Japanese financial-specif…

Language ModelingLanguage ModellingLarge Language Model