AceGPT, Localizing Large Language Models in Arabic

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Huang, Yu, Fei, Zhu, Jianqing, Sun, Xuening, Cheng, Hao, Song, Dingjie, Chen, Zhihong, Alharthi, Abdulmohsen, An, Bang, He, Juncai, Liu, Ziche, Zhang, Zhiyi, Chen, Junying, Li, Jianquan, Wang, Benyou, Zhang, Lian, Sun, Ruoyu, Wan, Xiang, Li, Haizhou, Xu, Jinchao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909156417470464
author Huang, Huang
Yu, Fei
Zhu, Jianqing
Sun, Xuening
Cheng, Hao
Song, Dingjie
Chen, Zhihong
Alharthi, Abdulmohsen
An, Bang
He, Juncai
Liu, Ziche
Zhang, Zhiyi
Chen, Junying
Li, Jianquan
Wang, Benyou
Zhang, Lian
Sun, Ruoyu
Wan, Xiang
Li, Haizhou
Xu, Jinchao
author_facet Huang, Huang
Yu, Fei
Zhu, Jianqing
Sun, Xuening
Cheng, Hao
Song, Dingjie
Chen, Zhihong
Alharthi, Abdulmohsen
An, Bang
He, Juncai
Liu, Ziche
Zhang, Zhiyi
Chen, Junying
Li, Jianquan
Wang, Benyou
Zhang, Lian
Sun, Ruoyu
Wan, Xiang
Li, Haizhou
Xu, Jinchao
contents This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. To address this, the paper proposes a comprehensive solution that includes further pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic, alongside Reinforcement Learning with AI Feedback (RLAIF) employing a reward model attuned to local culture and values. The goal is to cultivate culturally cognizant and value-aligned Arabic LLMs capable of accommodating the diverse, application-specific needs of Arabic-speaking communities. Comprehensive evaluations reveal that the resulting model, dubbed `AceGPT', sets the state-of-the-art standard for open Arabic LLMs across various benchmarks. Codes, data, and models are in https://github.com/FreedomIntelligence/AceGPT.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12053
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AceGPT, Localizing Large Language Models in Arabic
Huang, Huang
Yu, Fei
Zhu, Jianqing
Sun, Xuening
Cheng, Hao
Song, Dingjie
Chen, Zhihong
Alharthi, Abdulmohsen
An, Bang
He, Juncai
Liu, Ziche
Zhang, Zhiyi
Chen, Junying
Li, Jianquan
Wang, Benyou
Zhang, Lian
Sun, Ruoyu
Wan, Xiang
Li, Haizhou
Xu, Jinchao
Computation and Language
This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. To address this, the paper proposes a comprehensive solution that includes further pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic, alongside Reinforcement Learning with AI Feedback (RLAIF) employing a reward model attuned to local culture and values. The goal is to cultivate culturally cognizant and value-aligned Arabic LLMs capable of accommodating the diverse, application-specific needs of Arabic-speaking communities. Comprehensive evaluations reveal that the resulting model, dubbed `AceGPT', sets the state-of-the-art standard for open Arabic LLMs across various benchmarks. Codes, data, and models are in https://github.com/FreedomIntelligence/AceGPT.
title AceGPT, Localizing Large Language Models in Arabic
topic Computation and Language
url https://arxiv.org/abs/2309.12053