大模型
arxiv.org ·
CFO 与 LLM 的相遇
arXiv 论文《CFOs Meet LLMs》提出让 LLM 扮演特定公司在特定日期的 CFO，对 2002–2025 年 Duke–Federal Reserve CFO 调查的每位上市公司 CFO 生成经济乐观度评分。结果显示该评分能预测 CFO 的实际回答，在控制企业、年季固定效应及人类 CFO 滞后回答后关系依然存在，且准确率随输入信息增加而提升；对自身企业乐观度和企业营收预期两个问题也呈现相同模式。作者认为在适当条件下，LLM 未来或可作为高管的“数字孪生”，为金融研究与政策提供可扩展、高频的预期数据。
AI推荐理由 arXiv 论文（q-fin.CP），作者为 John R. Graham、Campbell R. Harvey、Manish Jha，摘要明确：用 LLM 扮演特定公司在特定日期的 CFO，对 2002–2025 年 Duke–Federal Reserve CFO 调查的受访者生成经济乐观度评分，并检验其能否预测 CFO 实际回答；在加入企业、年季固定效应及人类 CFO 滞后回答控制变量后关系仍存在，且准确率随提供给 LLM 的信息增加而提高。新信息在于把 LLM 用作高管“数字孪生”以生成可扩展、高频的预期数据，属金融研究与政策应用方向；局限是摘要仅称“may in the future”，未给出实际部署或因果结论，且为预印本、未经同行评审。
72
正文
Quantitative Finance > Computational Finance
arXiv:2606.13812 (q-fin)
[Submitted on 11 Jun 2026 (v1), last revised 21 Sep 2026 (this version, v2)]
Title:CFOs Meet LLMs
Authors:John R. Graham, Campbell R. Harvey, Manish Jha
View a PDF of the paper titled CFOs Meet LLMs, by John R. Graham and 2 other authors
View PDF
Abstract:Business sentiment is a closely watched economic signal, but measuring it is slow and costly: surveys typically reach only a few hundred firms, arrive periodically, and take time to compile. We show that large language models hold the potential to address these shortcomings. We prompt an LLM to role-play as the CFO of a specific company on a specific date, for every public-company CFO who responded to the Duke--Federal Reserve CFO Survey between 2002 and 2025, and answer a question about economy-wide optimism. The LLM-generated optimism score predicts the individual CFO's actual answer, even in specifications that include firm and year-quarter fixed effects as well as a control variable measuring the human CFO's lagged response. Accuracy increases with the information provided to the LLM, and the relation persists under quarterly aggregation. We find the same patterns hold for two other questions measuring CFO expectations: the respondent's optimism about their own firm and their expectation of own-firm revenues. With appropriate conditioning, LLMs may in the future be able to serve as digital twins of executives, offering scalable, high-frequency expectations data for financial research and policy.
Comments:
Subjects:
Computational Finance (q-fin.CP); General Finance (q-fin.GN)
Cite as:
arXiv:2606.13812 [q-fin.CP]
(or
arXiv:2606.13812v2 [q-fin.CP] for this version)
https://doi.org/10.48550/arXiv.2606.13812
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Manish Jha [view email]
[v1]
Thu, 11 Jun 2026 18:32:12 UTC (300 KB)
[v2]
Mon, 21 Sep 2026 14:49:48 UTC (322 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled CFOs Meet LLMs, by John R. Graham and 2 other authors
View PDF
view license
Current browse context:
q-fin.CP
new
|
recent
| 2026-06
Change to browse by:
q-fin
q-fin.GN
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)