Research Article

CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS

Volume: 17 October 22, 2026
EN TR

CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS

Abstract

Large language models (LLMs) are increasingly used as experimental subjects in behavioral and economic research. However, it remains unclear whether their decisions reflect stable preferences or context-dependent responses. This study examines intertemporal choice behavior in LLMs within a controlled experimental framework. We implement a fully factorial design across four models (ChatGPT, Gemini, Copilot, and Claude), varying persona (financially stressed vs. disciplined), delay (1 vs. 6 months), reward magnitude (650–900 $), and prompt framing (direct vs. human-like). Each condition is repeated to approximate response distributions. Results show that LLM behavior is structured but not preference-stable. Decisions are primarily driven by persona conditioning: financially disciplined agents choose delayed rewards significantly more often than stressed agents. Delay and reward magnitude affect choices in line with temporal discounting, while prompt framing has negligible effects. We interpret these findings by conceptualizing LLMs as context-dependent behavioral simulators rather than agents with stable preferences. The contribution is not to establish human equivalence, but to identify the internal consistency and structure of LLM responses under controlled variation. Overall, the results highlight the importance of experimental design and suggest that LLM outputs should be understood as conditional simulations rather than stable expressions of preference.

Keywords

Large language models, Behavioral economics, Intertemporal choice, Experimental design, Context-dependent preferences

References

  1. Aher, G. V., Arriaga, R. I., & Kalai, A. T. (2023). Using large language models to simulate multiple humans and replicate human subject studies. In A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, & J. Scarlett (Eds.), Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202, pp. 337–371). PMLR. https://proceedings.mlr.press/v202/aher23a.html
  2. Anthropic. (2025, May 22). System card: Claude Opus 4 & Claude Sonnet 4. Anthropic. https://www.anthropic.com/claude-4-system-card
  3. Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023). Out of one, many: Using language models to simulate human samples. Political Analysis, 31(3), 337–351. https://doi.org/10.1017/pan.2023.2
  4. Ashokkumar, A., Hewitt, L., Ghezae, I., & Willer, R. (2026). Large language models can predict the results of social science experiments. Nature, 656, 115–122. https://doi.org/10.1038/s41586-026-10742-x
  5. Binz, M., & Schulz, E. (2023). Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences, 120(6), e2218523120. https://doi.org/10.1073/pnas.2218523120
  6. Bowman, S. R. (2023). Eight things to know about large language models. https://doi.org/10.48550/arXiv.2304.00612
  7. Chen, L., Zaharia, M., & Zou, J. (2024). How is ChatGPT's behavior changing over time? Harvard Data Science Review, 6(2). https://doi.org/10.1162/99608f92.5317da47
  8. Dillon, D., Tandon, N., Gu, Y., & Gray, K. (2023). Can AI language models replace human participants? Trends in Cognitive Sciences, 27(7), 597–600. https://doi.org/10.1016/j.tics.2023.04.008
  9. Frederick, S., Loewenstein, G., & O’Donoghue, T. (2002). Time discounting and time preference: A critical review. Journal of Economic Literature, 40(2), 351–401. https://doi.org/10.1257/jel.40.2.351
  10. Gao, C., Lan, X., Li, N., Yuan, Y., Ding, J., Zhou, Z., Xu, F., & Li, Y. (2024). Large language models empowered agent-based modeling and simulation: A survey and perspectives. Humanities and Social Sciences Communications, 11(1), Article 1259. https://doi.org/10.1057/s41599-024-03611-3
APA
Başbuğ, A. K. (2026). CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS. Journal of Academic Approaches, 17, 1-31. https://doi.org/10.54688/ayd.1932565
AMA
1.Başbuğ AK. CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS. JAA. 2026;17:1-31. doi:10.54688/ayd.1932565
Chicago
Başbuğ, Ali Kemal. 2026. “CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS”. Journal of Academic Approaches 17 (October): 1-31. https://doi.org/10.54688/ayd.1932565.
EndNote
Başbuğ AK (October 1, 2026) CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS. Journal of Academic Approaches 17 1–31.
IEEE
[1]A. K. Başbuğ, “CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS”, JAA, vol. 17, pp. 1–31, Oct. 2026, doi: 10.54688/ayd.1932565.
ISNAD
Başbuğ, Ali Kemal. “CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS”. Journal of Academic Approaches 17 (October 1, 2026): 1-31. https://doi.org/10.54688/ayd.1932565.
JAMA
1.Başbuğ AK. CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS. JAA. 2026;17:1–31.
MLA
Başbuğ, Ali Kemal. “CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS”. Journal of Academic Approaches, vol. 17, Oct. 2026, pp. 1-31, doi:10.54688/ayd.1932565.
Vancouver
1.Ali Kemal Başbuğ. CONTEXT OVER LANGUAGE: PERSONA-DRIVEN INTERTEMPORAL CHOICE IN LARGE LANGUAGE MODELS. JAA. 2026 Oct. 1;17:1-31. doi:10.54688/ayd.1932565