Using cognitive psychology to understand GPT-3
This work provides insights into the capabilities and limitations of large language models for researchers in AI and cognitive science, though it is incremental in applying existing psychological tools.
The study assessed GPT-3's cognitive abilities using experiments from cognitive psychology, finding it performs similarly or better than humans in some tasks like decision-making and multi-armed bandit tasks, but fails in others like causal reasoning and is sensitive to small perturbations.
We study GPT-3, a recent large language model, using tools from cognitive psychology. More specifically, we assess GPT-3's decision-making, information search, deliberation, and causal reasoning abilities on a battery of canonical experiments from the literature. We find that much of GPT-3's behavior is impressive: it solves vignette-based tasks similarly or better than human subjects, is able to make decent decisions from descriptions, outperforms humans in a multi-armed bandit task, and shows signatures of model-based reinforcement learning. Yet we also find that small perturbations to vignette-based tasks can lead GPT-3 vastly astray, that it shows no signatures of directed exploration, and that it fails miserably in a causal reasoning task. These results enrich our understanding of current large language models and pave the way for future investigations using tools from cognitive psychology to study increasingly capable and opaque artificial agents.