Simulating Human Memory with Language Models

ArXi:2605.25680v1 Announce Type: cross Language models are increasingly being deployed as user simulators, but their memory is far reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a human-like way.