Guardado en:
Detalles Bibliográficos
Autores principales: Luo, Jiayuan, Yang, Songhua, Qiu, Xiaoling, Chen, Panyu, Nai, Yufei, Zeng, Wenxuan, Zhang, Wentao, Jiang, Xinke
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.13866
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914691838640128
author Luo, Jiayuan
Yang, Songhua
Qiu, Xiaoling
Chen, Panyu
Nai, Yufei
Zeng, Wenxuan
Zhang, Wentao
Jiang, Xinke
author_facet Luo, Jiayuan
Yang, Songhua
Qiu, Xiaoling
Chen, Panyu
Nai, Yufei
Zeng, Wenxuan
Zhang, Wentao
Jiang, Xinke
contents Large Language Models (LLMs) like ChatGPT and GPT-4 have demonstrated impressive proficiency in comprehending and generating natural language. However, they encounter difficulties when tasked with adapting to specialized domains such as accounting. To address this challenge, we introduce Kuaiji, a tailored Accounting Large Language Model. Kuaiji is meticulously fine-tuned using the Baichuan framework, which encompasses continuous pre-training and supervised fine-tuning processes. Supported by CAtAcctQA, a dataset containing large genuine accountant-client dialogues, Kuaiji exhibits exceptional accuracy and response speed. Our contributions encompass the creation of the first Chinese accounting dataset, the establishment of Kuaiji as a leading open-source Chinese accounting LLM, and the validation of its efficacy through real-world accounting scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13866
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kuaiji: the First Chinese Accounting Large Language Model
Luo, Jiayuan
Yang, Songhua
Qiu, Xiaoling
Chen, Panyu
Nai, Yufei
Zeng, Wenxuan
Zhang, Wentao
Jiang, Xinke
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) like ChatGPT and GPT-4 have demonstrated impressive proficiency in comprehending and generating natural language. However, they encounter difficulties when tasked with adapting to specialized domains such as accounting. To address this challenge, we introduce Kuaiji, a tailored Accounting Large Language Model. Kuaiji is meticulously fine-tuned using the Baichuan framework, which encompasses continuous pre-training and supervised fine-tuning processes. Supported by CAtAcctQA, a dataset containing large genuine accountant-client dialogues, Kuaiji exhibits exceptional accuracy and response speed. Our contributions encompass the creation of the first Chinese accounting dataset, the establishment of Kuaiji as a leading open-source Chinese accounting LLM, and the validation of its efficacy through real-world accounting scenarios.
title Kuaiji: the First Chinese Accounting Large Language Model
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.13866