Generative artificial intelligence holds enormous potential to revolutionize decision-making processes, from everyday to high-stake scenarios. However, as many decisions carry social implications, for AI to be a reliable assistant for decision-making it is crucial that it is able to capture the balance between self-interest and the interest of others. We investigate the ability of three of the most advanced chatbots to predict dictator game decisions across 78 experiments with human participants from 12 countries. We find that only GPT-4 (not Bard nor Bing) correctly captures qualitative behavioral patterns, identifying three major classes of behavior: self-interested, inequity-averse, and fully altruistic. Nonetheless, GPT-4 consistently overestimates other-regarding behavior, inflating the proportion of inequity-averse and fully altruistic participants. This bias has significant implications for AI developers and users.
Latest posts by Ryan Watkins (see all)
- Learning activities in technology-enhanced learning: A systematic review of meta-analyses and second-order meta-analysis in higher education - April 29, 2024
- Legal Aspects for Software Developers Interested in Generative AI Applications - April 28, 2024
- Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments - April 24, 2024