CFOs Meet LLMs

arXiv:2606.13812 · q-fin.CP, q-fin.GN · Submitted 2026-06-11 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Quantitative Finance. The day in quantitative finance: models of markets, risk and prices.

Ruth: We're looking at the paper: "CFOs Meet LLMs".

Warren: Here's the gist of the paper. 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 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.

Ruth: The LLM framework approximates how an executive is likely to respond given their information set and prior answers, providing an individual-level benchmark for the predictable component of managerial expectations.

Warren: The authors propose and evaluate a method for generating synthetic CFO expectations with large language models (LLMs).

Ruth: They prompt the LLM to role-play as the CFO of a specific public company at a specific point in time, supplying the model with the firm’s industry, revenue, headcount, and geographic footprint.

Paper summary: Ruth: What’s interesting is that this isn't just about getting a general market feeling; it’s about linking the digital twin sentiment to the human response in a very direct way >

Warren: They found that the predictive accuracy of this LLM forecast changes depending on how much information you give it, showing a dose-response relationship >

Iris: Specifically, when you supply the LLM model with three or more prior responses from that CFO, the fit increases to nearly fifty percent because that’s when it gets really accurate >

Ruth: It’s not just about the firm profile; they found that conditioning on each CFO respondent’s own history significantly anchors the persona to the individual rather than just a group type >

Warren: And when you look at it aggregated, even after controlling for things like macroeconomic benchmarks such as the Michigan Consumer Sentiment Index and some professional forecast of real GDP growth, the mean LLM optimism remains a significant predictor of mean CFO optimism >

Iris: They also validated this individual-level prediction within a single firm by matching every synthetic score to the response of the actual CFO at that same firm in that same quarter >

Ruth: So, they’re showing that even though these individual survey responses weren't used in training the model, these predictions are out-of-corpus with respect to those specific human answers >

Warren: That individual predictive content is what they point to as notable because it goes against prior work suggesting managerial expectations are just noisy reflections of public information >

Conclusion: Ruth: So, looking at "CFOs Meet LLMs," the main thing is that this method generates synthetic CFO expectations using large language models >

Warren: The key finding is that the LLM score is a significant predictor of the actual CFO’s response at the individual level >

Iris: And accuracy scales with how much information you provide to that AI model >

Ruth: Plus, aggregate results show that mean LLM optimism stays a significant predictor of mean CFO optimism even when you control for external economic benchmarks >

Warren: The paper suggests that in the future, these large language models might be useful as synthetic executives, especially when they are conditioned on a rich firm- and respondent-level context >

Iris: This offers the prospect of a real-time, scalable individual-level sentiment measure for both practitioners and policymakers >

Duke University · Georgia State University

q-fin.CP, q-fin.GN

Submitted: 2026-06-11

Updated: 2026-11-15

Comments: 21 pages, 4 tables, 1 figure

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 91/100

The gist: 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…

Key concepts

LLM-generated optimism score
This is a metric produced by an LLM that simulates what a CFO would likely say. It goes beyond simple firm averages by predicting the specific answer of an individual CFO based on their company details and past responses, offering a more granular view of sentiment.
Conditioning on Executive History
A key technique where the LLM is fed the specific history and prior forecasts of an individual CFO. This anchors the model's prediction to that person's unique behavior rather than just a generic firm type, significantly boosting accuracy in predicting individual responses.
Dose-Response Relationship
This describes how increasing the amount of relevant information provided to the LLM affects its predictive accuracy. The results show that supplying more prior expectation data—specifically over three responses—monotonically increases the model's fit to actual CFO answers.
Synthetic Executives
The idea that LLMs can function as realistic, simulated executives. By conditioning them on rich context like firm and respondent-level details, they can serve as scalable tools for generating synthetic data to study economic sentiment in a way traditional surveys cannot.

Terminology

Summary

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 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. p. 0

Where the paper says it

Graham† Campbell R. Harvey† Manish Jha‡ †Duke University and NBER ‡Georgia State University 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.

The LLM framework approximates how an executive is likely to respond given their information set and prior answers, providing an individual-level benchmark for the predictable component of managerial expectations. p. 2
Where the paper says it

(2016) show that CFO expectations contain extrapolative components that predict future investment. Our LLM framework approximates how an executive is likely to respond given their information set and prior answers, providing an individual-level benchmark for the predictable component of managerial expectations.

p. 2
Where the paper says it

(2016) show that CFO expectations contain extrapolative components that predict future investment. Our LLM framework approximates how an executive is likely to respond given their information set and prior answers, providing an individual-level benchmark for the predictable component of managerial expectations.

Methodology for Synthetic Data Generation

The authors propose and evaluate a method for generating synthetic CFO expectations with large language models (LLMs). They prompt the LLM to role-play as the CFO of a specific public company at a specific point in time, supplying the model with the firm’s industry, revenue, headcount, and geographic footprint. p. 1

Where the paper says it

We make no claim that the model reasons in the same manner as the executive. We prompt the LLM to role-play as the CFO of a specific public company at a specific point in time, supplying the model with the firm’s industry, revenue, headcount, and geographic footprint, and imposing an information cutoff matching the date of the actual survey wave.

The system prompt directs the model to adopt a comprehensive analytical framework that mirrors the decision-making process of a financial executive at a given point in time. p. 7
Where the paper says it

In this particular quarter, our prompting strategy successfully prevents the model from incorporating knowledge of subsequent events: a model with access to post-cutoff information would almost certainly produce markedly more pessimistic forecasts for this period. The system prompt directs the model to adopt a comprehensive analytical framework that mirrors the decision-making process of a financial executive at a given point in time.

Conditioning on Executive History

A key methodological contribution relative to earlier persona-based work is that we condition on each CFO respondent’s own history. Supplying the model with a person’s prior answers, and with the LLM’s own prior forecasts for that person, anchors the persona to the individual rather than to a group or a generic firm type. p. 2

Where the paper says it

(2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this. Supplying the model with a person’s prior answers, and with the LLM’s own prior forecasts for that person, anchors the persona to the individual rather than to a group or a generic firm type, and we find that it limits the collapse.

This conditioning significantly improves individual-level prediction, as prompts built from the firm profile alone or combined with history explain 9-10% of the variation in individual responses. p. 3
Where the paper says it

A parallel pattern holds for the breadth of firm characteristics provided to the LLM: prompts that include the full company profile produce better predictions than sparse prompts. These dose–response relationships, where richer conditioning inputs (dose) produce systematically stronger or more accurate model outputs (response), indicate that the model is using the conditioning information rather than guessing, and they highlight the conditions under which synthetic executives most faithfully reproduce human responses.

Predictive Accuracy and Information Dosage

The predictive accuracy of the LLM forecast varies with the information provided, showing dose–response relationships. With respect to providing the LLM model with the CFO respondent’s own history of expectations, the fit increases monotonically with the amount of information provided. p. 3

Where the paper says it

We find that more information leads to better forecasts. With respect to providing the LLM model with the CFO respondent’s own history of expectations, the fit increases monotonically with the amount of information provided: from anR 2 of approximately 10% when no prior CFO responses are available, to roughly 33% with one to three historic CFO responses, to nearly 50% when more than three prior responses are supplied (Table 2, Panel B).

The results indicate that when more than three prior responses are supplied to the model, it increases to nearly half (R2 = 0. p. 3
Where the paper says it

We find that more information leads to better forecasts. With respect to providing the LLM model with the CFO respondent’s own history of expectations, the fit increases monotonically with the amount of information provided: from anR 2 of approximately 10% when no prior CFO responses are available, to roughly 33% with one to three historic CFO responses, to nearly 50% when more than three prior responses are supplied (Table 2, Panel B).

49).

Robustness and Macroeconomic Benchmarking

The LLM framework introduces an LLM-based measure of CFO-level economic sentiment and provides the first individual-level, within-firm validation of LLM-simulated survey responses. The relationship between human CFO sentiment and digital twin sentiment is robust to aggregation, as the mean LLM optimism remains a significant predictor of mean CFO optimism even after controlling for macroeconomic benchmarks like the Michigan Consumer Sentiment Index and the SPF professional forecast of real GDP growth. p. 9

Where the paper says it

Macro Forecasts and Consumer Sentiment We also compare a within-quarter aggregation of the LLM’s economy-wide optimism scores against two established measures of macroeconomic expectations. The first is the mean yearahead real GDP growth forecast (drgdp5) from the Survey of Professional Forecasters (SPF), administered quarterly by the Federal Reserve Bank of Philadelphia and drawing on roughly 30 to 40 professional forecasters at financial institutions, consulting firms, and academic organizations.

Implications for Research and Policy

The scalability opens several research designs that were previously infeasible, such as generating daily or weekly LLM sentiment scores for a full cross-section of public firms to study policy shocks. The findings suggest that in the future, LLMs may be useful as synthetic executives, particularly when conditioned on a rich firm- and respondent-level context. p. 0

Where the paper says it

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.

This offers the prospect of a real-time, scalable, individual-level sentiment measure for practitioners and policymakers. p. 4
Where the paper says it

Because LLM agents need not behave like humans, individual-level fidelity is not something we can assume, and in our setting it emerges only after we condition each persona on the respondent’s own history, without which instruction-tuned models collapse toward modal opinions (Santurkar et al. Our framework introduces an LLM-based measure of CFO-level economic sentiment and provides the first individual-level, within-firm validation of LLM-simulated survey responses, approximating private forecasts using an information set of public data and a respondent’s own past answers.

The LLM complements the human survey rather than replaces it. p. 2
Where the paper says it

Supplying the model with a person’s prior answers, and with the LLM’s own prior forecasts for that person, anchors the persona to the individual rather than to a group or a generic firm type, and we find that it limits the collapse. In our sample, the within-quarter dispersion of LLM scores is about 75% of the dispersion in the human panel.

Conclusion

The paper presents a method for generating synthetic CFO expectations using large language models. Four main findings emerge: the LLM score is a significant predictor of the actual CFO’s response at the individual level, predictive accuracy scales with the information provided, and aggregate results show that mean LLM optimism remains a significant predictor of mean CFO optimism even after controlling for macroeconomic benchmarks. p. 0

Where the paper says it

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.

The analysis suggests that in the future, LLMs may be useful as synthetic executives. p. 0
Where the paper says it

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. Keywords: Large language models; CFO survey; Managerial expectations; Business sentiment; Synthetic surveys; Digital twins; Belief formation JEL Classification: C55, D84, E27, G30, G41 Version: September 8, 2026.

References

Aher et al. (2023) Argyle et al. p. 3

Where the paper says it

Argyle et al. (2023) show that LLM-generated synthetic survey populations closely match the distributional properties of real human samples, and Suh et al.

p. 3
Where the paper says it

Argyle et al. (2023) show that LLM-generated synthetic survey populations closely match the distributional properties of real human samples, and Suh et al.

(2023) Bai et al. p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

(2023) Bali et al. p. 4
Where the paper says it

The first simulates a population of forecasters to recover the dispersion of beliefs rather than any one person’s answer. Bali et al.

p. 4
Where the paper says it

The first simulates a population of forecasters to recover the dispersion of beliefs rather than any one person’s answer. Bali et al.

(2026) Balke and Petersen (2002) Barrero (2025) Baslandze et al. p. 1
Where the paper says it

For each of 6,075 survey responses from public companies 1Fried et al. (2026) demonstrate that the Duke-Fed CFO survey tracks future inflation; and Baslandze et al.

p. 1
Where the paper says it

For each of 6,075 survey responses from public companies 1Fried et al. (2026) demonstrate that the Duke-Fed CFO survey tracks future inflation; and Baslandze et al.

(2026) Ben-David et al. p. 0
Where the paper says it

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. Keywords: Large language models; CFO survey; Managerial expectations; Business sentiment; Synthetic surveys; Digital twins; Belief formation JEL Classification: C55, D84, E27, G30, G41 Version: September 8, 2026.

p. 0
Where the paper says it

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. Keywords: Large language models; CFO survey; Managerial expectations; Business sentiment; Synthetic surveys; Digital twins; Belief formation JEL Classification: C55, D84, E27, G30, G41 Version: September 8, 2026.

(2013) Bordalo et al. (2020) Boutros et al. p. 5
Where the paper says it

First, we impose information cutoffs that instruct the model not to access post-survey data, and any respondent history we supply is itself dated strictly before the cutoff. We find supportive evidence that this instruction was followed in that the first-quarter 2020 LLM forecast does not anticipate the COVID-era reduction in optimism that occurred ex post.

p. 5
Where the paper says it

First, we impose information cutoffs that instruct the model not to access post-survey data, and any respondent history we supply is itself dated strictly before the cutoff. We find supportive evidence that this instruction was followed in that the first-quarter 2020 LLM forecast does not anticipate the COVID-era reduction in optimism that occurred ex post.

(2025) Brand et al. p. 5
Where the paper says it

, 2024), inflation expectations (Faria-e Castro and Leibovici, 2024; Wu et al. , 2025), market research (Brand et al.

p. 5
Where the paper says it

, 2024), inflation expectations (Faria-e Castro and Leibovici, 2024; Wu et al. , 2025), market research (Brand et al.

(2023) Brown (1910) Cameron et al. p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

(2011) Cao et al. p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

(2024) Carlini et al. p. 5
Where the paper says it

(2025), Sarkar and Vafa (2025), and Gao et al. Memorization refers broadly to the model’s retention of facts from its training corpus (Carlini et al.

p. 5
Where the paper says it

(2025), Sarkar and Vafa (2025), and Gao et al. Memorization refers broadly to the model’s retention of facts from its training corpus (Carlini et al.

(2023) Coibion et al. p. 1
Where the paper says it

1 Graham (2022) further documents the central role that executive expectations play in corporate investment and planning decisions. Coibion et al.

p. 1
Where the paper says it

1 Graham (2022) further documents the central role that executive expectations play in corporate investment and planning decisions. Coibion et al.

(2018) Cook et al. p. 1
Where the paper says it

Coibion et al. (2018) use a large survey of corporate managers and show that their macroeconomic expectations are widely dispersed, depart systematically from professional forecasts, and feed back into company decisions.

p. 1
Where the paper says it

Coibion et al. (2018) use a large survey of corporate managers and show that their macroeconomic expectations are widely dispersed, depart systematically from professional forecasts, and feed back into company decisions.

(2023) Correia (2015) Dillion et al. p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

p. 2
Where the paper says it

Models tuned on human feedback are known to compress the diversity of human opinion: Santurkar et al. (2023) find that such models place nearly all of their probability mass on a single answer to opinion-survey questions, matching the modal view of a group rather than the spread of views within it, and that prompting the model to adopt a group’s persona does not repair this.

(2023) Faria-e Castro and Leibovici (2024) Fried et al. p. 5
Where the paper says it

, 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al. , 2024), inflation expectations (Faria-e Castro and Leibovici, 2024; Wu et al.

p. 5
Where the paper says it

, 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al. , 2024), inflation expectations (Faria-e Castro and Leibovici, 2024; Wu et al.

(2026) Gao et al. p. 5
Where the paper says it

(2023), Lopez-Lira et al. (2025), Sarkar and Vafa (2025), and Gao et al.

p. 5
Where the paper says it

(2023), Lopez-Lira et al. (2025), Sarkar and Vafa (2025), and Gao et al.

(2025) Gennaioli et al. p. 1
Where the paper says it

Operating in the intersection of corporate strategy and the macroeconomic environment, they aggregate information about customers, suppliers, competitors, and capital markets into forward-looking assessments of business activity. Research spanning a quarter century has shown that measured CFO expectations are economically meaningful: Gennaioli et al.

p. 1
Where the paper says it

Operating in the intersection of corporate strategy and the macroeconomic environment, they aggregate information about customers, suppliers, competitors, and capital markets into forward-looking assessments of business activity. Research spanning a quarter century has shown that measured CFO expectations are economically meaningful: Gennaioli et al.

(2016) Glasserman and Lin (2023) Gormsen and Huber (2024) Goulding et al. p. 4
Where the paper says it

Our framework introduces an LLM-based measure of CFO-level economic sentiment and provides the first individual-level, within-firm validation of LLM-simulated survey responses, approximating private forecasts using an information set of public data and a respondent’s own past answers. 2 We also address the memorization concerns raised by Glasserman and Lin 2For a survey of machine learning in economics and finance, see Korinek (2023).

p. 4
Where the paper says it

Our framework introduces an LLM-based measure of CFO-level economic sentiment and provides the first individual-level, within-firm validation of LLM-simulated survey responses, approximating private forecasts using an information set of public data and a respondent’s own past answers. 2 We also address the memorization concerns raised by Glasserman and Lin 2For a survey of machine learning in economics and finance, see Korinek (2023).

(2026) Graham et al. p. 0
Where the paper says it

CFOs Meet LLMs John R. Graham† Campbell R.

p. 0
Where the paper says it

CFOs Meet LLMs John R. Graham† Campbell R.

(2019) Graham and Harvey (2001) Gu et al. p. 0
Where the paper says it

Graham† Campbell R. Harvey† Manish Jha‡ †Duke University and NBER ‡Georgia State University 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.

p. 0
Where the paper says it

Graham† Campbell R. Harvey† Manish Jha‡ †Duke University and NBER ‡Georgia State University 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.

(2020) Hansen et al. p. 5
Where the paper says it

First, we impose information cutoffs that instruct the model not to access post-survey data, and any respondent history we supply is itself dated strictly before the cutoff. We find supportive evidence that this instruction was followed in that the first-quarter 2020 LLM forecast does not anticipate the COVID-era reduction in optimism that occurred ex post.

p. 5
Where the paper says it

First, we impose information cutoffs that instruct the model not to access post-survey data, and any respondent history we supply is itself dated strictly before the cutoff. We find supportive evidence that this instruction was followed in that the first-quarter 2020 LLM forecast does not anticipate the COVID-era reduction in optimism that occurred ex post.

(2025) Hansen and McMahon (2016) Heaton et al. p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

(2017) Henning et al. p. 4
Where the paper says it

A second strand is cautionary. Henning et al.

p. 4
Where the paper says it

A second strand is cautionary. Henning et al.

(2025) Horton et al. p. 3
Where the paper says it

(2024) find that chatbot behavior in standard economic games is broadly similar to that of human subjects, though not identical to it. Manning and Horton (2025) further demonstrate that grounding LLM personas in economic theory and calibrating them against human data substantially improves predictive fidelity in novel settings, providing a methodological foundation 3

p. 3
Where the paper says it

(2024) find that chatbot behavior in standard economic games is broadly similar to that of human subjects, though not identical to it. Manning and Horton (2025) further demonstrate that grounding LLM personas in economic theory and calibrating them against human data substantially improves predictive fidelity in novel settings, providing a methodological foundation 3

(2023) Jha et al. p. 0
Where the paper says it

Graham† Campbell R. Harvey† Manish Jha‡ †Duke University and NBER ‡Georgia State University 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.

p. 0
Where the paper says it

Graham† Campbell R. Harvey† Manish Jha‡ †Duke University and NBER ‡Georgia State University 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.

(2024) Kapoor and Narayanan (2023) Korinek (2023) Li et al. p. 5
Where the paper says it

3 Our setting satisfies the no-leakage condition formalized by Ludwig et al. (2025), since the target variable was contractually excluded from the training corpus, and it avoids the most severe category in the leakage taxonomy of Kapoor and Narayanan (2023), in which the outcome to be predicted is itself present in the training data.

p. 5
Where the paper says it

3 Our setting satisfies the no-leakage condition formalized by Ludwig et al. (2025), since the target variable was contractually excluded from the training corpus, and it avoids the most severe category in the leakage taxonomy of Kapoor and Narayanan (2023), in which the outcome to be predicted is itself present in the training data.

(2024) Lopez-Lira et al. p. 5
Where the paper says it

, 2020; Lopez-Lira and Tang, 2023; Uddin et al. , 2024; Wang et al.

p. 5
Where the paper says it

, 2020; Lopez-Lira and Tang, 2023; Uddin et al. , 2024; Wang et al.

(2025) Loughran and McDonald (2011) Ludwigson (2004) Malmendier and Tate (2015) Manning and Horton (2025) Mei et al. p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

(2024) Newey and West (1987) Park et al. p. 4
Where the paper says it

We go further by testing whether the LLM persona predicts the response of the specific human at the same firm and quarter, and by showing how that fidelity depends on the information the model is given. In a non-economic setting, Park et al.

p. 4
Where the paper says it

We go further by testing whether the LLM persona predicts the response of the specific human at the same firm and quarter, and by showing how that fidelity depends on the information the model is given. In a non-economic setting, Park et al.

(2026) Sarkar and Vafa (2025) Shrout and Fleiss (1979) Suh et al. p. 5
Where the paper says it

(2023), Lopez-Lira et al. (2025), Sarkar and Vafa (2025), and Gao et al.

p. 5
Where the paper says it

(2023), Lopez-Lira et al. (2025), Sarkar and Vafa (2025), and Gao et al.

(2025) Tetlock (2007) Tetlock et al. p. 5
Where the paper says it

The final section offers some conclusions. Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al.

p. 5
Where the paper says it

The final section offers some conclusions. Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al.

(2008) Uddin et al. p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

p. 5
Where the paper says it

Construction of the LLM Optimism Scores We construct LLM-generated forecasts to simulate the expectations of individual CFOs participating in The CFO Survey, conducted quarterly by Duke University and the Federal Reserve sentiment classification (Tetlock, 2007; Tetlock et al. , 2008; Loughran and McDonald, 2011; Hansen and McMahon, 2016), financial analysis (Cao et al.

(2024) Wang et al. p. 5
Where the paper says it

, 2020; Lopez-Lira and Tang, 2023; Uddin et al. , 2024; Wang et al.

p. 5
Where the paper says it

, 2020; Lopez-Lira and Tang, 2023; Uddin et al. , 2024; Wang et al.

(2026) Wu et al. p. 0
Where the paper says it

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. Keywords: Large language models; CFO survey; Managerial expectations; Business sentiment; Synthetic surveys; Digital twins; Belief formation JEL Classification: C55, D84, E27, G30, G41 Version: September 8, 2026.

p. 0
Where the paper says it

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. Keywords: Large language models; CFO survey; Managerial expectations; Business sentiment; Synthetic surveys; Digital twins; Belief formation JEL Classification: C55, D84, E27, G30, G41 Version: September 8, 2026.

(2025) Bybee (2025). p. 0
Where the paper says it

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 paper is 2606. p. 1
Where the paper says it

However, despite their informational value, managerial expectations are expensive to collect (Bloom and Van Reenen, 2007), available only at a fixed frequency, and are limited to the several hundred companies whose executives choose to participate in a given survey wave. In this paper, we explore whether it is possible to generate credible CFO-style expectations at scale, without the cost, the small sample, and the delay of a human survey.

p. 1
Where the paper says it

However, despite their informational value, managerial expectations are expensive to collect (Bloom and Van Reenen, 2007), available only at a fixed frequency, and are limited to the several hundred companies whose executives choose to participate in a given survey wave. In this paper, we explore whether it is possible to generate credible CFO-style expectations at scale, without the cost, the small sample, and the delay of a human survey.

13812. EVERY sentence must end with a reference token > p. 0
Where the paper says it

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.

--- Page 1 ---

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 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. The LLM framework approximates how an executive is likely to respond given their information set and prior answers, providing an individual-level benchmark for the predictable component of managerial expectations.

Aher et al. (2023) Argyle et al. (2023) Bai et al. (2023) Bali et al. (2026) Balke and Petersen (2002) Barrero (2025) Baslandze et al. (2026) Ben-David et al. (2013) Bordalo et al. (2020) Boutros et al. (2025) Brand et al. (2023) Brown (1910) Cameron et al. (2011) Cao et al. (2024) Carlini et al. (2023) Coibion et al. (2018) Cook et al. (2023) Correia (2015) Dillion et al. (2023) Faria-e Castro and Leibovici (2024) Fried et al. (2026) Gao et al. (2025) Gennaioli et al. (2016) Glasserman and Lin (2023) Gormsen and Huber (2024) Goulding et al. (2026) Graham et al. (2019) Graham and Harvey (2001) Gu et al. (2020) Hansen et al. (2025) Hansen and McMahon (2016) Heaton et al. (2017) Henning et al. (2025) Horton et al. (2023) Jha et al. (2024) Kapoor and Narayanan (2023) Korinek (2023) Li et al. (2024) Lopez-Lira et al. (2025) Loughran and McDonald (11) Ludwigson (2004) Malmendier and Tate (2015) Manning and Horton (2025) Mei et al. p. 3

Where the paper says it

(2024) find that chatbot behavior in standard economic games is broadly similar to that of human subjects, though not identical to it. Manning and Horton (2025) further demonstrate that grounding LLM personas in economic theory and calibrating them against human data substantially improves predictive fidelity in novel settings, providing a methodological foundation 3

(2024) Newey and West (1987) Park et al. (2026) Sarkar and Vafa (2025) Shrout and Fleiss (1979) Suh et al. (2025) Tetlock (2007) Tetlock et al. (2008) Uddin et al. (2024) Wang et al. (2026) Wu et al. (2025). The paper is 2606.13812. EVERY sentence must end with a reference token >

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Scale synthetic survey generation for high-frequency policy shocks by using LLMs to generate daily or weekly sentiment scores for a full crosssection of public firms, circumventing traditional quarterly constraints in event-study designs.

  2. Enable synthetic survey experiments by prompting LLMs with counterfactual company characteristics to study how expectations respond to specific policy shocks, which has no natural analog in human data.

  3. Implement history conditioning as the primary mechanism for improving individual-level prediction accuracy, allowing the model to approximate private forecasts by using the respondent’s own past answers and the LLM’s own prior forecasts for that person.

  4. Improve synthetic executive fidelity by including a rich information set, specifically ensuring prompts include both the full company profile and conditioning on the respondent’s own history, which increases the fit to nearly 50% in the best-case scenarios.

  5. Develop a scalable, individual-level sentiment measure for practitioners and policymakers that can offer a real-time, scalable, individual-level sentiment measure by approximating private forecasts using an information set of public data and a respondent’s own past answers.

Abstract

Business sentiment is closely watched, but measurement is slow and costly: surveys reach a limited number of firms, arrive periodically, and take time to field and compile. We show that large language models hold the potential to address some of 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 from 2002- 2025. We find that LLM-generated forecasts reasonably match the cross-section of CFO expectations, with accuracy increasing with the amount of information provided to the LLM.

Sources

Related papers