Frontiers: Can Large Language Models Capture Human Preferences?

References

• Andersen S, Harrison GW, Lau MI, Rutström EE (2008) Eliciting risk and time preferences. Econometrica 76(3):583–618.Crossref, Google Scholar
• Andreoni J, Sprenger C (2012) Estimating time preferences from convex budgets. Amer. Econom. Rev. 102(7):3333–3356.Crossref, Google Scholar
• Angeletos G-M, Laibson D, Repetto A, Tobacman J, Weinberg S (2001) The hyperbolic consumption model: Calibration, simulation, and empirical evaluation. J. Econom. Perspect. 15(3):47–68.Crossref, Google Scholar
• Argyle LP, Busby EC, Fulda N, Gubler JR, Rytting C, Wingate D (2023) Out of one, many: Using language models to simulate human samples. Political Anal. 31(3):337–351.Crossref, Google Scholar
• Atlas SA, Johnson EJ, Payne JW (2017) Time preferences and mortgage choice. J. Marketing Res. 54(3):415–429.Crossref, Google Scholar
• Ayres I, Katz TK, Regev T (2023) Languages and future-oriented economic behavior-Experimental evidence for causal effects. Proc. Natl. Acad. Sci. USA 120(7):e2208871120.Crossref, Google Scholar
• Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J. Machine Learn. Res. 3(January):993–1022.Google Scholar
• Boroditsky L (2001) Does language shape thought?: Mandarin and English speakers’ conceptions of time. Cognitive Psych. 43(1):1–22.Crossref, Google Scholar
• Bradford D, Courtemanche C, Heutel G, McAlvanah P, Ruhm C (2017) Time preferences and consumer behavior. J. Risk Uncertainty 55:119–145.Crossref, Google Scholar
• Brand J, Israeli A, Ngwe D (2023) Using GPT for market research. Preprint, submitted March 21, http://dx.doi.org/10.2139/ssrn.4395751.Google Scholar
• Brucks M, Toubia O (2023) Prompt architecture can induce methodological artifacts in large language models. Preprint, submitted June 19, http://dx.doi.org/10.2139/ssrn.4484416.Google Scholar
• Bubeck S, Chandrasekaran V, Eldan R, Gehrke J, Horvitz E, Kamar E, Lee P, et al. (2023) Sparks of artificial general intelligence: Early experiments with GPT-4. Preprint, submitted March 22, https://arxiv.org/abs/2303.12712.Google Scholar
• Chen MK (2013) The effect of language on economic behavior: Evidence from savings rates, health behaviors, and retirement assets. Amer. Econom. Rev. 103(2):690–731.Crossref, Google Scholar
• Chen S, Cronqvist H, Ni S, Zhang F (2017) Languages and corporate savings behavior. J. Corporate Finance 46:320–341.Crossref, Google Scholar
• Chen Y, Liu TX, Shan Y, Zhong S (2023) The emergence of economic rationality of GPT. Proc. Natl. Acad. Sci. USA 120(51):e2316205120.Google Scholar
• Coda-Forno J, Witte K, Jagadish AK, Binz M, Akata Z, Schulz E (2023) Inducing anxiety in large language models increases exploration and bias. Preprint, submitted April 21, https://arxiv.org/abs/2304.11111.Google Scholar
• Dillion D, Tandon N, Gu Y, Gray K (2023) Can AI language models replace human participants? Trends Cognitive Sci. 27(7):597–600.Crossref, Google Scholar
• Falk A, Becker A, Dohmen T, Enke B, Huffman D, Sunde U (2018) Global evidence on economic preferences. Quart. J. Econom. 133(4):1645–1692.Crossref, Google Scholar
• Frederick S, Loewenstein G, O’Donoghue T (2002) Time discounting and time preference: A critical review. J. Econom. Literature 40(2):351–401.Crossref, Google Scholar
• Frederick S, Novemsky N, Wang J, Dhar R, Nowlis S (2009) Opportunity cost neglect. J. Consumer Res. 36(4):553–561.Crossref, Google Scholar
• Gui G, Toubia O (2023) The challenge of using LLMs to simulate human behavior: A causal inference perspective. Preprint, submitted December 24, https://arxiv.org/abs/2312.15524.Google Scholar
• Harrison GW, Lau MI, Williams MB (2002) Estimating individual discount rates in Denmark: A field experiment. Amer. Econom. Rev. 92(5):1606–1617.Crossref, Google Scholar
• Hesketh B (2000) Time perspective in career-related choices: Applications of time-discounting principles. J. Vocational Behav. 57(1):62–84.Crossref, Google Scholar
• Holt CA, Laury SK (2002) Risk aversion and incentive effects. Amer. Econom. Rev. 92(5):1644–1655.Crossref, Google Scholar
• Horton JJ (2023) Large language models as simulated economic agents: What can we learn from Homo silicus? Preprint, submitted January 18, https://arxiv.org/abs/2301.07543.Google Scholar
• Li X, Hsee CK (2021) The psychology of marginal utility. J. Consumer Res. 48(1):169–188.Crossref, Google Scholar
• Liu B, Ash JT, Goel S, Krishnamurthy A, Zhang C (2022) Transformers learn shortcuts to automata. Preprint, submitted October 19, https://arxiv.org/abs/2210.10749.Google Scholar
• Lu Y, Bartolo M, Moore A, Riedel S, Stenetorp P (2022) Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. Muresan S, Nakov P, Villavicencio A, eds. Proc. 60th Annual Meeting Assoc. Comput. Linguistics, vol. 1: Long Papers (Association for Computational Linguistics, Dublin, Ireland), 8086–8098.Google Scholar
• Maital S, Maital S (1976) Time preference, delay of gratification and the intergenerational transmission of economic inequality: A behavioral theory of income distribution. Working paper, Foerder Institute for Economic Research, Department of Economics, Tel-Aviv University, Tel Aviv, Israel.Google Scholar
• Millar MG, Tesser A (1986) Thought-induced attitude change: The effects of schema structure and commitment. J. Personality Soc. Psych. 51(2):259–269.Crossref, Google Scholar
• Mischel W, Ayduk O, Mendoza-Denton R (2003) Sustaining delay of gratification over time: A hot-cool systems perspective. Loewenstein G, Read D, Baumeister R, eds. Time and Decision: Economic and Psychological Perspectives on Intertemporal Choice (Russell Sage Foundation, New York), 175–200.Google Scholar
• O’Donoghue T, Rabin M (1999) Doing it now or later. Amer. Econom. Rev. 89(1):103–124.Crossref, Google Scholar
• OpenAI (2023) Introduction to the OpenAI Chat API. Accessed May 2, 2023, https://platform.openai.com/docs/guides/chat/introduction.Google Scholar
• Osei-Tutu F, Weill L (2021) How language shapes bank risk taking. J. Financial Services Res. 59:47–68.Crossref, Google Scholar
• Pender JL (1996) Discount rates and credit markets: Theory and evidence from rural India. J. Development Econom. 50(2):257–296.Crossref, Google Scholar
• Salisbury LC, Feinberg FM (2008) Future preference uncertainty and diversification: The role of temporal stochastic inflation. J. Consumer Res. 35(2):349–359.Crossref, Google Scholar
• Shelley MK (1993) Outcome signs, question frames and discount rates. Management Sci. 39(7):806–815.Link, Google Scholar
• Shelley MK (1994) Gain/loss asymmetry in risky intertemporal choice. Organ. Behav. Human Decision Processes 59(1):124–159.Crossref, Google Scholar
• Sussman AB, Hershfield HE, Netzer O (2023) Consumer financial decision making: Where we’ve been and where we’re going. J. Assoc. Consumer Res. 8(4):365–372.Google Scholar
• Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv. Neural Inform. Processing Systems 30:6000–6010.Google Scholar
• Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi E, Le QV, et al. (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inform. Processing Systems 35:24824–24837.Google Scholar
• Wilson TD, Schooler JW (1991) Thinking too much: Introspection can reduce the quality of preferences and decisions. J. Personality Soc. Psych. 60(2):181–192.Crossref, Google Scholar
• Zauberman G, Kim BK, Malkoc SA, Bettman JR (2009) Discounting time and time discounting: Subjective time perception and intertemporal preferences. J. Marketing Res. 46(4):543–556.Crossref, Google Scholar
• Zhang Y, Backurs A, Bubeck S, Eldan R, Gunasekar S, Wagner T (2022) Unveiling transformers with Lego: A synthetic reasoning task. Preprint, submitted June 9, https://arxiv.org/abs/2206.04301.Google Scholar