評估大型語言模型的提示工程在ESG新聞分類問題的一致性效能;Evaluating the Coherence of Prompt Engineering in ESG News Classification using Large Language Models

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/95456

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/95456

Title:	評估大型語言模型的提示工程在ESG新聞分類問題的一致性效能;Evaluating the Coherence of Prompt Engineering in ESG News Classification using Large Language Models
Authors:	鄭善仁;Cheng, Shan-Jen
Contributors:	資訊工程學系
Keywords:	生成式AI;ESG;文本分類;自然語言處理;資料標注;Generative AI;ESG;Text classification;Natural Language Processing;Data Annotation
Date:	2024-07-10
Issue Date:	2024-10-09 16:52:12 (UTC+8)
Publisher:	國立中央大學
Abstract:	近幾年興起的大型語言模型，如OpenAI 公司的 GPT4 和 Meta公司的 Llama和Google公司的Gemini等模型，在理解、分析和生成自然語言方面取得了突破性進展，這些技術的應用為知識和資訊的提取提供了更準確的方式。同時，環境永續的重要性也在逐年浮現，若能將最新的AI技術與環境永續做結合，有望能對地球的永續發展做出重要貢獻。因此，本論文旨在探討基於生成式AI（Gen-AI）技術，特別是使用Generative Pre-trained Transformer 3.5（GPT3.5）模型和 Gemini 模型，來進行環境、社會和公司治理（ESG）相關新聞的資料標注。我們將通過這些先進的自然語言處理 (Natural Language Processing, NLP) 技術，賦予模型理解並標注 ESG 相關內容的能力。進一步地，我們將探討這些標注過的新聞對於訓練 BERT 分類模型的影響，並評估其在ESG新聞分類任務中的性能提升。實驗結果將提供對於基於生成式 AI的資料標注技術在提高相關領域資料準確性上的洞見，同時為進一步發展應用於ESG領域的NLP技術提供實證支持。本研究將推動生成式AI在資訊分類和相關任務中的應用，促使更有效的資訊萃取和準確的資料標注。實驗結果顯示，ESG新聞經過 GPT3.5 和 Gemini 標注後再予以BERT進行分類訓練能提升準確率，為NLP的應用在ESG領域開啟了新的可能性。透過生成式 AI 的先進語義理解和標注技術，我們成功地為ESG新聞注入了更豐富的語境和內容標籤，使得BERT模型在分類任務中能更全面、準確地理解文章的主題和內容。 ;Recent years have seen rapid development of large language models (LLMs) like GPT, LLaMA, and Gemini, making breakthroughs in understanding, analyzing, and generating natural language. As environmental sustainability gains prominence, integrating AI with it can positively impact sustainable development. This thesis explores using generative AI (Gen-AI) technology, specifically GPT3.5 and Gemini models, for automatic annotation of environmental, social, and governance (ESG) news. It empowers models to understand and label ESG content through advanced natural language processing. The impact of these annotated news on training BERT classification models and performance improvements in ESG news classification is investigated. The results provide insights into using Gen-AI automatic annotation to improve data accuracy and empirical support for developing Natural Language Processing (NLP) technologies applied to ESG. Promoting Gen-AI application in information classification enables efficient extraction and accurate annotation. Annotation ESG news with Gen-AI models, then training with BERT improves classification accuracy, opening possibilities for NLP in ESG through advanced semantic understanding and annotation.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	67	View/Open

社群 sharing

Loading...