Studying and improving reasoning in humans and machines
This work provides insights into machine reasoning for AI researchers and cognitive psychologists, though it is incremental in comparing existing models with established human experiments.
The study compared reasoning in large language models and humans using cognitive psychology experiments, finding that while early LLMs showed human-like reasoning errors, these limitations largely disappeared in more recent models, and humans and machines responded differently to prompting strategies.
In the present study, we investigate and compare reasoning in large language models (LLM) and humans using a selection of cognitive psychology tools traditionally dedicated to the study of (bounded) rationality. To do so, we presented to human participants and an array of pretrained LLMs new variants of classical cognitive experiments, and cross-compared their performances. Our results showed that most of the included models presented reasoning errors akin to those frequently ascribed to error-prone, heuristic-based human reasoning. Notwithstanding this superficial similarity, an in-depth comparison between humans and LLMs indicated important differences with human-like reasoning, with models limitations disappearing almost entirely in more recent LLMs releases. Moreover, we show that while it is possible to devise strategies to induce better performance, humans and machines are not equally-responsive to the same prompting schemes. We conclude by discussing the epistemological implications and challenges of comparing human and machine behavior for both artificial intelligence and cognitive psychology.