Kuaiji: the First Chinese Accounting Large Language Model
Jiayuan Luo, Songhua Yang, Xiaoling Qiu, Panyu Chen, Yufei Nai,, Wenxuan Zeng, Wentao Zhang, Xinke Jiang

TL;DR
Kuaiji is the first Chinese accounting large language model, fine-tuned with a new dataset and demonstrating high accuracy and speed in real-world accounting tasks.
Contribution
Introduction of Kuaiji, the first Chinese accounting LLM, with a new dataset and open-source implementation validated in practical scenarios.
Findings
High accuracy in accounting tasks
Fast response times
Effective in real-world scenarios
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHistorical and Literary Studies · History and Theory of Mathematics
MethodsAttention Is All You Need · Linear Layer · Dense Connections · Label Smoothing · Adam · Softmax · Multi-Head Attention · Layer Normalization · Residual Connection · Absolute Position Encodings
