arXiv 2304.030872024-10-17cs.CL

使用ChatGPT的思维链探究社交媒体立场检测

Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media

College of Big Data and Internet, Shenzhen Technology University（深圳技术大学大数据与互联网学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Shenzhen X-Institute（深圳X研究院）；Academy of Cyber, Beijing（北京网络研究院）

Bowen Zhang, Xianghua Fu, Daijun Ding, Hu Huang, Genan Dai, Nan Yin, Yangyang Li, Liwen Jing

备注：: arXiv admin note: text overlap with arXiv:2212.14548

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文探究了无参数的思维链（CoT）方法结合ChatGPT在社交媒体立场检测任务中的有效性，展示了其相比传统方法在准确率上的优越性及相关挑战。

摘要：

立场检测预测文本中对目标的态度，随社交媒体兴起备受关注。传统方法含机器学习、早期深度神经网络及预训练微调模型。然而，随着ChatGPT（GPT-3.5）等超大型预训练语言模型（VLPLMs）的演进，传统方法面临部署挑战。无需反向传播训练的无参数思维链（CoT）方法成为极具前景的替代方案。本文检验了CoT在立场检测任务中的有效性，展示了其卓越的准确率并讨论了相关挑战。

英文摘要：

Stance detection predicts attitudes towards targets in texts and has gained attention with the rise of social media. Traditional approaches include conventional machine learning, early deep neural networks, and pre-trained fine-tuning models. However, with the evolution of very large pre-trained language models (VLPLMs) like ChatGPT (GPT-3.5), traditional methods face deployment challenges. The parameter-free Chain-of-Thought (CoT) approach, not requiring backpropagation training, has emerged as a promising alternative. This paper examines CoT's effectiveness in stance detection tasks, demonstrating its superior accuracy and discussing associated challenges.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。