English(EN) Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls

大型语言模型以79.7%的准确率从非结构化财报电话会议中提取关键绩效指标

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-04 20:40

研究人员开发了从非结构化财报电话会议记录中提取关键绩效指标（KPI）的新基准和方法。他们发现，在结构化SEC文件中训练的模型难以泛化到财报电话会议的对话性质。为解决此问题，他们提出了一种使用大型语言模型（LLM）进行开放式提取的系统，在人类评估中达到了79.7%的准确率。 AI

影响为从非结构化财报电话会议数据中提取财务关键绩效指标提供了新的基准和基于大型语言模型的方法。

排序理由该集群包含一篇学术论文，详细介绍了从财务财报电话会议中提取关键绩效指标的新基准和方法。[lever_c_demoted from research: ic=2 ai=0.4]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Rasmus T. Aavang, Rasmus Tjalk-B{\o}ggild, Alexandre Iolov, Giovanni Rizzi, Mike Zhang, Johannes Bjerva · 2026-05-06 04:00

Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls

arXiv:2605.03147v1 Announce Type: new Abstract: Earnings calls are a key source of financial information about public companies. However, extracting information from these calls is difficult. Unlike the templatic filings required by the U.S. Securities and Exchange Commission (SE…
arXiv cs.CL TIER_1 English(EN) · Johannes Bjerva · 2026-05-04 20:40

Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls

Earnings calls are a key source of financial information about public companies. However, extracting information from these calls is difficult. Unlike the templatic filings required by the U.S. Securities and Exchange Commission (SEC) to report a company's financial situation, ea…