arXiv cs.CL· Ahmet Efe, Shivank Sapra, Bilal Ahmed·· 11 小时前AI 评分27
财报电话会议文本能预测财务重述吗？评估公开公司信息之外的文本价值
Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information
AI 导读
对比 109 通财务重述前的财报电话会议与 218 通匹配对照会议后发现，文本分类器虽优于随机猜测，但相比仅用公开公司信息的模型并无排名增益，后者得分还略高。重拟合后文本增益的 95% 区间为 -0.05 至 0.11 AUROC，仍可能包含实际价值。大语言模型得分更高，但在 66% 的掩码转录稿中直接说出对应股票代码，且其发布时间晚于这些重述事件。
正文 · 原文
Abstract:Financial restatements correct errors in previously published financial reports. Could managers' language in earnings calls warn of them in advance? Comparing 109 calls that precede restatements with 218 matched control calls, we find that the text predicts restatements but adds no detectable ranking gain beyond public firm information. A text classifier beats chance, largely because of restatements tied to special-purpose acquisition companies, but a model using only public information scores slightly higher. With refitting, the 95% interval for the gain from adding text (-0.05 to 0.11 AUROC) still leaves room for a meaningful benefit. A large language model scores higher, but we show that it names the exact ticker in 66% of masked transcripts, and it was released after the restatements occurred. Our results suggest that finding new warning signs in call text requires a public-information baseline and a check of what a language model already knows.
| Comments: | 8 pages, 2 figures, 2 tables |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2611.01123 [cs.CL] |
| (or arXiv:2611.01123v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01123 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahmet Efe [view email]
[v1]
Sat, 31 Oct 2026 17:10:34 UTC (47 KB)
来源：arXiv cs.CL · arxiv.org