arrow
返回

Using large language models to create narrative events

delete2024-10-22
delete0
delete
OA
AI
V
Valentina Bartalesi *
E
Emanuele Lenzi
C
C. De Martino
DOI:10.7717/peerj-cs.2242delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Narratives play a crucial role in human communication, serving as a means to convey experiences, perspectives, and meanings across various domains. They are particularly significant in scientific communities, where narratives are often utilized to explain complex phenomena and share knowledge. This article explores the possibility of integrating large language models (LLMs) into a workflow that, exploiting the Semantic Web technologies, transforms raw textual data gathered by scientific communities into narratives. In particular, we focus on using LLMs to automatically create narrative events, maintaining the reliability of the generated texts. The study provides a conceptual definition of narrative events and evaluates the performance of different smaller LLMs compared to the requirements we identified. A key aspect of the experiment is the emphasis on maintaining the integrity of the original narratives in the LLM outputs, as experts often review texts produced by scientific communities to ensure their accuracy and reliability. We first perform an evaluation on a corpus of five narratives and then on a larger dataset comprising 124 narratives. LLaMA 2 is identified as the most suitable model for generating narrative events that closely align with the input texts, demonstrating its ability to generate high-quality narrative events. Prompt engineering techniques are then employed to enhance the performance of the selected model, leading to further improvements in the quality of the generated texts.
Keyword:
Large language models
Narratives
Events
Semantic web
Digital humanities
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

PeerJ Computer Science 封面图
PeerJ Computer Science
IF:
2.5
论文数:
3.4K
被引数:
6.9K

机构

C
consiglio nazionale delle ricerche (cnr)
学者数:
6.2W
论文数: 5.7W
被引数: 48
引用论文

引用论文

err分享
err收藏
Brain areas underlying visual mental imagery and visual perception: an fMRI study
err2004-07-01
err0
PREAI
errGiorgio Ganis; William L Thompson; Stephen M Kosslyn
err分享
err收藏
Information visualisation for science and policy: engaging users and avoiding bias
err2014-03-01
err103
errOAAI
errMcInerny, Greg J.; Chen, Min; Freeman, Robin; Gavaghan, David; Meyer, Miriah; Rowland, Francis; Spiegelhalter, David J.; Stefaner, Moritz; Tessarolo, Geizi; Hortal, Joaquin
err分享
err收藏
err分享
err收藏
学者 查看更多内容