真实犯罪播客的叙事分析：基于知识图谱增强的大语言模型
Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models
AI总结：
本研究通过知识图谱增强的大语言模型分析真实犯罪播客叙事，与经典NLP方法对比，发现KGLLM在准确性、鲁棒性和主题总结上更优。
摘要：
叙事数据跨越所有学科，为读者或观众提供了一个连贯的世界模型。机器学习和大语言模型（LLMs）的最新进展在分析自然语言方面取得了巨大进步。然而，大语言模型（LLMs）在处理复杂叙事弧以及包含相互冲突信息的叙事时仍面临困难。近期研究表明，通过外部知识库增强的LLMs可以提高所生成模型的准确性和可解释性。在本工作中，我们分析了应用知识图谱（KGs）从经典自然语言处理（NLP）和LLM两种方法理解真实犯罪播客数据的有效性。我们直接将知识图谱增强的LLMs（KGLLMs）与经典方法在知识图谱构建、主题建模和情感分析方面进行比较。此外，KGLLM允许我们用自然语言查询知识库，并测试其事实性回答问题的能力。我们检验了模型对对抗性提示的鲁棒性，以测试模型处理冲突信息的能力。最后，我们应用经典方法来理解文本中更微妙的方面，如叙事构建中传闻的使用和情感，并提出未来方向。我们的结果表明，KGLLMs在多种指标上优于LLMs，对对抗性提示更具鲁棒性，并且更能够将文本总结为主题。
英文摘要：
Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics.
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。
