用大模型嵌入检测极端偏颇新闻，准确率超92%。
Embedding-Based Approaches to Hyperpartisan News Detection
- 用大模型生成文本嵌入，替代传统特征提取方法
- 在10折交叉验证下准确率达92%，优于先前83%的ELMo模型
- 适合关注政治偏见识别与内容安全的研究者
本报告描述了用于判断新闻文章是否具有极端偏颇性的系统。极端偏颇新闻以极端政治立场煽动公众分裂。采用的方法包括n-gram、情感分析，以及基于预训练ELMo模型的句子和文档表示。最佳系统使用大语言模型生成嵌入，在10折交叉验证下准确率达到约92%，显著优于此前基于预训练ELMo与双向LSTM的系统（准确率约83%）。
原文摘要 · Abstract (English)
In this report, I describe the systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news takes an extremely polarized political standpoint with an intention of creating political divide among the public. Several approaches, including n-grams, sentiment analysis, as well as sentence and document representations using pre-tained ELMo models were used. The best system is using LLMs for embedding generation achieving an accuracy of around 92% over the previously best system using pre-trained ELMo with Bidirectional LSTM which achieved an accuracy of around 83% through 10-fold cross-validation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。