Language-based game theory in the age of artificial intelligence

Abstract

Understanding human behaviour in decision problems and strategic interactions has wide-ranging applications in economics, psychology and artificial intelligence. Game theory offers a robust foundation for this understanding, based on the idea that individuals aim to maximize a utility function. However, the exact factors influencing strategy choices remain elusive. While traditional models try to explain human behaviour as a function of the outcomes of available actions, recent experimental research reveals that linguistic content significantly impacts decision-making, thus prompting a paradigm shift from outcome-based to language-based utility functions. This shift is more urgent than ever, given the advancement of generative AI, which has the potential to support humans in making critical decisions through language-based interactions. We propose sentiment analysis as a fundamental tool for this shift and take an initial step by analysing 61 experimental instructions from the dictator game, an economic game capturing the balance between self-interest and the interest of others, which is at the core of many social interactions. Our meta-analysis shows that sentiment analysis can explain human behaviour beyond economic outcomes. We discuss future research directions. We hope this work sets the stage for a novel game-theoretical approach that emphasizes the importance of language in human decisions.

Keywords: artificial intelligence; game theory; language-based utility functions.

Figure 1.

Forest plot of the meta-analysis of the sentiment associated with altruistic behaviour across the studies. One study [49] gets dropped from the meta-analysis, because GPT-4 estimates the same sentiments in all four conditions, therefore the study-level regression does not estimate the standard error. It is important to note that GPT-4 sentiment scores are in line with actual behaviour also in this study, as the mean giving did not significantly vary across conditions. Moreover, the same study does not get dropped in the robustness checks, all of which show a similar pattern of results.