arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.01039cs.CL
收藏

从事实到洞察:关于生成与评估用于解读财报电话会议的分析报告的研究

From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls

University of Sheffield(谢菲尔德大学);University of Manchester(曼彻斯特大学);Artificial Intelligence Research Center, AIST, Japan(日本国立先进工业科学技术研究院人工智能研究中心)

Tomas Goldsack, Yang Wang, Chenghua Lin, Chung-Chi Chen

AI总结:

本文研究多智能体LLM框架生成财报电话会议分析报告,并评估LLM在报告质量判断上与人类专家的一致性。

摘要:

本文探讨了大型语言模型(LLM)在生成和评估源自财报电话会议(Earnings Calls,ECs)的分析报告中的应用。为弥补当前研究空白,我们在一个多智能体框架中探索使用LLM生成分析报告,设计了专门的智能体,将多元观点和理想的分析主题引入报告生成过程。通过多项分析,我们考察了生成报告与人类撰写报告之间的一致性,以及单个智能体和智能体集体的影响。研究结果表明,引入额外智能体会使报告更具洞察力,尽管在大多数情况下,人类专家生成的报告仍然更受青睐。最后,我们处理了报告评估这一具有挑战性的问题,考察了LLM在不同设置下评估所生成报告质量的局限性与优势,揭示出其在多个维度上与人类专家存在显著相关性。

英文摘要:

This paper explores the use of Large Language Models (LLMs) in the generation and evaluation of analytical reports derived from Earnings Calls (ECs). Addressing a current gap in research, we explore the generation of analytical reports with LLMs in a multi-agent framework, designing specialized agents that introduce diverse viewpoints and desirable topics of analysis into the report generation process. Through multiple analyses, we examine the alignment between generated and human-written reports and the impact of both individual and collective agents. Our findings suggest that the introduction of additional agents results in more insightful reports, although reports generated by human experts remain preferred in the majority of cases. Finally, we address the challenging issue of report evaluation, we examine the limitations and strengths of LLMs in assessing the quality of generated reports in different settings, revealing a significant correlation with human experts across multiple dimensions.

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。

↑