Saved in:
Bibliographic Details
Main Authors: Leng, Xinyi, Liang, Jason, Mauro, Jack, Wang, Xu, Bertozzi, Andrea L., Chapman, James, Lin, Junyuan, Chen, Bohan, Ye, Chenchen, Daniel, Temple, Brantingham, P. Jeffrey
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.02435
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910685107060736
author Leng, Xinyi
Liang, Jason
Mauro, Jack
Wang, Xu
Bertozzi, Andrea L.
Chapman, James
Lin, Junyuan
Chen, Bohan
Ye, Chenchen
Daniel, Temple
Brantingham, P. Jeffrey
author_facet Leng, Xinyi
Liang, Jason
Mauro, Jack
Wang, Xu
Bertozzi, Andrea L.
Chapman, James
Lin, Junyuan
Chen, Bohan
Ye, Chenchen
Daniel, Temple
Brantingham, P. Jeffrey
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02435
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models
Leng, Xinyi
Liang, Jason
Mauro, Jack
Wang, Xu
Bertozzi, Andrea L.
Chapman, James
Lin, Junyuan
Chen, Bohan
Ye, Chenchen
Daniel, Temple
Brantingham, P. Jeffrey
Computation and Language
Machine Learning
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.
title Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.02435