在检索增强生成上下文中使用原子事实蕴含指标测量文本摘要事实性
Measuring text summarization factuality using atomic facts entailment metrics in the context of retrieval augmented generation
AI总结:
针对LLMs生成摘要易产生“幻觉”的问题,本项目提出一种基于Naive Bayes分类的方法,通过对比源文本评估LLMs生成摘要的事实性与内容准确性。
摘要:
自2022年引入ChatGPT以来,大型语言模型(LLMs)的使用显著增加,展示了其在各种应用中的价值。然而,企业和商业采用LLMs的一个主要挑战是它们倾向于生成不准确的信息,这种现象被称为“幻觉”。本项目提出了一种方法,用于估算LLMs生成的摘要与源文本相比的事实性。我们的方法利用Naive Bayes分类来评估所生成内容的准确性。
英文摘要:
The use of large language models (LLMs) has significantly increased since the introduction of ChatGPT in 2022, demonstrating their value across various applications. However, a major challenge for enterprise and commercial adoption of LLMs is their tendency to generate inaccurate information, a phenomenon known as "hallucination." This project proposes a method for estimating the factuality of a summary generated by LLMs when compared to a source text. Our approach utilizes Naive Bayes classification to assess the accuracy of the content produced.
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。