loading page

PowerPulse: Power Energy Chat Model with LLaMA Model Fine-tuned on Chinese and Power Sector Domain Knowledge
  • +6
  • qiong nong,
  • ChunLin Yin,
  • KunPeng Du,
  • HongCheng Zhang,
  • Li Yang,
  • Bin Yan,
  • Huang Xiang,
  • XiaoBo Wang,
  • Xuan Zhang
qiong nong
Yunnan University
Author Profile
ChunLin Yin
Yunnan Power Grid Co Ltd
Author Profile
KunPeng Du
Yunnan University
Author Profile
HongCheng Zhang
Yunnan Power Grid Co Ltd
Author Profile
Li Yang
Yunnan Power Grid Co Ltd
Author Profile
Bin Yan
Yunnan Power Grid Co Ltd
Author Profile
Huang Xiang
Yunnan Power Grid Co Ltd
Author Profile
XiaoBo Wang
Yunnan University
Author Profile
Xuan Zhang
Yunnan University

Corresponding Author:zhxuan@ynu.edu.cn

Author Profile

Abstract

Recently, Large-scale Language Models (LLMs) such as Chat Generative Pre-trained Transformer (ChatGPT) and Generative Pre-trained Transformer 4 (GPT-4) have demonstrated remarkable performance in the general domain. However, Inadaptability in a particular domain have led to hallucination for these LLMs when responding in specific domain contexts. The issue has attracted widespread attention, existing domain-centered fine-tuning efforts have predominantly focused on sectors like medical, financial, and legal, leaving critical areas such as power energy relatively unexplored. To bridge this gap, this paper introduces a novel power energy chat model called PowerPulse. Built upon the open and efficient foundation language models (LLaMA) architecture, PowerPulse is fine-tuned specifically on Chinese Power Sector Domain Knowledge. This work marks the inaugural application of the LLaMA model in the field of power energy. By leveraging pertinent pre-training data and instruction fine-tuning datasets tailored for the power energy domain, the PowerPulse model showcases exceptional performance in tasks such as text generation, summary extraction, and topic classification. Experimental results validate the efficacy of the PowerPulse model, making significant contributions to the advancement of specialized language models in specific domains.
08 Aug 2023Submitted to Expert Systems
08 Aug 2023Submission Checks Completed
08 Aug 2023Assigned to Editor
10 Aug 2023Reviewer(s) Assigned
16 Sep 2023Review(s) Completed, Editorial Evaluation Pending
18 Sep 2023Editorial Decision: Revise Minor
06 Oct 20231st Revision Received
09 Oct 2023Submission Checks Completed
09 Oct 2023Assigned to Editor
10 Oct 2023Reviewer(s) Assigned
02 Nov 2023Review(s) Completed, Editorial Evaluation Pending
05 Nov 2023Editorial Decision: Accept