The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Generative AI for Economic Research: Use Cases and Implications for Economists
Abstract
Generative artificial intelligence (AI) has the potential to revolutionize research. I analyze how large language models (LLMs) such as ChatGPT can assist economists by describing dozens of use cases in six areas: ideation and feedback, writing, background research, data analysis, coding, and mathematical derivations. I provide general instructions and demonstrate specific examples of how to take advantage of each of these, classifying the LLM capabilities from experimental to highly useful. I argue that economists can reap significant productivity gains by taking advantage of generative AI to automate micro-tasks. Moreover, these gains will grow as the performance of AI systems continues to improve. I also speculate on the longer-term implications of AI-powered cognitive automation for economic research. The online resources associated with this paper explain how to get started and will provide regular updates on the latest capabilities of generative AI in economics. (JEL A11, C45, D83, I23, O33)
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The application of LLMs in economics, particularly ChatGPT, is a relatively unexplored area.”
From Can ChatGPT forecast stock price movements? Return predictability and large language models (2026) · cites this paper as Korinek (2023)
In the citing paper
“There is cause for optimism: AI can complement workers by making them more efficient, helping them to produce higher quality work, or enabling them to take on new value-adding tasks (72–74).”
From The impact of generative artificial intelligence on socioeconomic inequalities and policy making (2024) · cites this paper as [74]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“The performance of LLMs improves pre-dictably according to so-called scaling laws, which are empirical regularities that have held for several generations of machine learning models (Kaplan et al. 2020).”
BackgroundOn the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 2×
“The reactions to the release of generative AI tools such as ChatGPT have been sharply divided: One camp of commentators label LLMs as nothing but “stochastic parrots” (Bender et al. 2021) or “advanced autocom-plete.””
BackgroundChain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models
Eloundou, T., Manning, S., Mishkin, P., & Rock, D. (2023) · arXiv · doi:10.48550/arxiv.2303.10130 · Cited by 2,330 · cited 1×
“Eloundou et al. (2023) and Felten et al. (2023) analyze how different occupations and industries will be affected by LLMs. Horton (2023) explores the use of LLMs as simulated economic agents.”
BackgroundExperimental evidence on the productivity effects of generative artificial intelligence
Noy, S., & Zhang, W. (2023) · Science · doi:10.1126/science.adh2586 · Cited by 2,150 · cited 1×
“Noy and Zhang (2023) demonstrate in a controlled experiment that ChatGPT made writers 40 percent faster while improving output quality and helping writers with weaker skills more, thereby reducing output inequality.”
BackgroundSparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Gentzkow, M. A., Kelly, B., & Taddy, M. A. (2019) · Journal of Economic Literature · doi:10.1257/jel.20181020 · Cited by 1,353
Emergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.01815 · Cited by 1,102 · cited 1×
“…example, when DeepMind developed AlphaZero, a chess computer that used massive computing power to learn chess by itself without any human input, it learned the game well enough within 24 hours to beat all other chess computers in the world, and of course all humans (Silver et al. 2017).”
MethodTraining Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2176 · Cited by 932
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929
Out of One, Many: Using Language Models to Simulate Human Samples
Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023) · Political Analysis · doi:10.1017/pan.2023.2 · Cited by 783
Idea Generation and the Quality of the Best Idea
Girotra, K., Terwiesch, C., & Ulrich, K. T. (2010) · Management Science · doi:10.1287/mnsc.1090.1144 · Cited by 755
Mathematical Capabilities of ChatGPT
Frieder, S., Pinchetti, L., Chevalier, C., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P., & Berner, J. (2023) · neural information processing systems · doi:10.52202/075280-1205 · Cited by 754
ChatGPT for (Finance) research: The Bananarama Conjecture
Dowling, M., & Lucey, B. M. (2023) · Finance research letters · doi:10.1016/j.frl.2023.103662 · Cited by 648
Can ChatGPT forecast stock price movements? Return predictability and large language models
Lopez-Lira, A., & Tang, Y. (2026) · Journal of Financial Economics · doi:10.1016/j.jfineco.2026.104335 · Cited by 425
Mathematical Capabilities of ChatGPT
Frieder, S., Pinchetti, L., Chevalier, A., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P. C., & Berner, J. (2023) · arXiv · doi:10.48550/arxiv.2301.13867 · Cited by 385
Compute Trends Across Three Eras of Machine Learning
Sevilla, J., Heim, L., Ho, A., Besiroglu, T., Hobbhahn, M., & Villalobos, P. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891914 · Cited by 363
Faith and Fate: Limits of Transformers on Compositionality
Dziri, N., Lu, X., Sclar, M., Li, X. (., Jiang, L., Lin, B. Y., Welleck, S., West, P., Bhagavatula, C., Bras, R. L., et al. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-3081 · Cited by 335 · cited 1×
“Dziri et al. (2023) show that LLMs also have difficulties in handling tasks that demand intricate multistep reasoning.”
BackgroundLarge Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
Horton, J., Filippas, A., & Manning, B. (2023) · National Bureau of Economic Research · doi:10.3386/w31122 · Cited by 329
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., & Kaplan, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.08073 · Cited by 326
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
Jiao, W., Wang, W., Huang, J.-T., Wang, X., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2301.08745 · Cited by 317
The Impact of AI on Developer Productivity: Evidence from GitHub Copilot
Peng, S., Kalliamvakou, E., Cihon, P., & Demirer, M. (2023) · arXiv · doi:10.48550/arxiv.2302.06590 · Cited by 287
Mollick, E. R., & Mollick, L. (2023) · doi:10.2139/ssrn.4391243 · Cited by 278 · cited 1×
“There has been a burst of literature on generative AI in economics in recent months, focused primarily on LLMs. Cowen and Tabarrok (2023) and Mollick and Mollick (2023) describe strategies for how to deploy LLMs for teaching and learning.”
BackgroundHow will Language Modelers like ChatGPT Affect Occupations and Industries?Preprint
Felten, E. W., Raj, M., & Seamans, R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4375268 · Cited by 228
Predictability and Surprise in Large Generative Models
Ganguli, D., Hernandez, D., Lovitt, L., Askell, A., Bai, Y., Chen, A., Conerly, T., Dassarma, N., Drain, D., Elhage, N., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533229 · Cited by 207 · cited 1×
“An interesting phenomenon about many of these emergent capabilities is that they initially even surprise the creators of these systems (Ganguli et al. 2022).”
BackgroundUniversal and Transferable Adversarial Attacks on Aligned Language Models
Zou, A., Wang, Z., Carlini, N., Nasr, M., Kolter, J. Z., & Fredrikson, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15043 · Cited by 197
AI and Its Impact on Creativity and Diversity: An Empirical Study of LLM-Generated Product Ideas
Terwiesch, C., Meincke, L., Girotra, K., Mollick, E. R., Nave, G., & Ulrich, K. T. (2023) · doi:10.2139/ssrn.4526071 · Cited by 174
Language Models and Cognitive Automation for Economic Research
Korinek, A. (2023) · doi:10.3386/w30957 · Cited by 129
Self-citationFaith and Fate: Limits of Transformers on Compositionality
Dziri, N., Lu, X., Sclar, M., Li, X. L., Jiang, L., Lin, B. Y., West, P., Bhagavatula, C., Bras, R. L., Hwang, J. D., et al. (2023) · arXiv · Cited by 124
Frontier AI Regulation: Managing Emerging Risks to Public Safety
Anderljung, M., Barnhart, J., Korinek, A., Leung, J., O'Keefe, C., Whittlestone, J., Avin, S., Brundage, M., Bullock, J., Cass-Beggs, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.03718 · Cited by 77
Self-citationStructured information extraction from complex scientific text with fine-tuned large language models
Dunn, A., Dagdelen, J., Walker, N., Lee, S., Rosen, A. S., Ceder, G., Persson, K., & Jain, A. (2022) · arXiv · doi:10.48550/arxiv.2212.05238 · Cited by 67
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Li, K., Hopkins, A. K., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2022) · arXiv · doi:10.48550/arxiv.2210.13382 · Cited by 61
Pretrained Language Models are Symbolic Mathematics Solvers too!Preprint
Noorbakhsh, K., Sulaiman, M., Sharifi, M., Roy, K., & Jamshidi, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03501 · Cited by 16
Generation Next: Experimentation with AI
Charness, G., Jabarian, B., & List, J. A. (2023) · National Bureau of Economic Research · doi:10.3386/w31679 · Cited by 15
Aligned with Whom? Direct and Social Goals for AI Systems
Korinek, A., & Balwit, A. (2022) · National Bureau of Economic Research · doi:10.3386/w30017 · Cited by 13
Self-citationEconSentGPT: A Universal Economic Sentiment Engine?Preprint
Ardekani, A. M., Bertz, J., Dowling, M., & Long, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4405779 · Cited by 3
Gpt-3.5 Hallucinates Nonexistent Citations: Evidence from EconomicsPreprint
Buchanan, J. A., & Shapoval, O. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4472220 · Cited by 2
Research works printed but not linked: 5
- Agrawal, Ajay, Joshua Gans, and Avi Goldfarb. 2018. Prediction Machines: The Simple Economics of Artificial Intelligence. Boston, MA: Harvard Business Review Press.
- Tabarrok Alexander T., 2023, GMU Working Paper in Economics, 23
- Frank, Robert H. 1991. "Positional Externalities." In Strategy and Choice, edited by Richard Zeckhauser, 25-47. Cambridge, MA: MIT Press.
- Keynes, John Maynard. 1936. The General Theory of Employment, Interest, and Money. London: Palgrave Macmillan.
- Alan, 1950, Mind, 59, 433
Cited by
Sorted by citations
Can ChatGPT forecast stock price movements? Return predictability and large language models
Lopez-Lira, A., & Tang, Y. (2026) · Journal of Financial Economics · doi:10.1016/j.jfineco.2026.104335 · Cited by 425
The impact of generative artificial intelligence on socioeconomic inequalities and policy making
Capraro, V., Lentsch, A., Acemoglu, D., Akgun, S., Akhmedova, A., Bilancini, E., Bonnefon, J.-F., Brañas-Garza, P., Butera, L., Douglas, K. M., et al. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae191 · Cited by 371
“There is currently little legislation preventing the use of deepfakes in political campaigns, although there are some steps in this direction.”
Budhathoki, T., Zirar, A., Njoya, E. T., & Timsina, A. (2024) · Studies in Higher Education · doi:10.1080/03075079.2024.2333937 · Cited by 280
“(Korinek 2023, 1281) ChatGPT can be a complementary teaching-learning aid for students (Ali et al. 2024).”
BackgroundGenerative AI in innovation and marketing processes: A roadmap of research opportunities
Cillo, P., & Rubera, G. (2024) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-024-01044-7 · Cited by 256
“For instance, it is estimated that the cost of training GPT-4 is over $100 million (Korinek, 2023 ).”
Human-AI agency in the age of generative AI
Krakowski, S. M. (2025) · Information and Organization · doi:10.1016/j.infoandorg.2025.100560 · Cited by 223
Metadata
- Authors
- Korinek, A.
- Affiliations
- Brookings Institution (US)
- Corresponding author
- Korinek, Anton
- ORCID
- Korinek, Anton
- Venue
- Journal of Economic Literature
- Publisher
- American Economic Association
- Published
- 2023-12-01
- Volume
- 61
- Issue
- 4
- Pages
- 1281-1317
- ISSN
- 0022-0515 (ISSN-L)
- OpenAlex
- W4389615177
- Cited by
- 293
- References
- 38
- Citations by year
- 2026: 111 · 2025: 109 · 2024: 65 · 2023: 7
- FWCI
- 27.53
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Economic Literature (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- generative AI, large language models, ChatGPT, economic research, research productivity, cognitive automation, academic writing, background research, data analysis, coding, mathematical derivation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
