Open access
Sep 2026
Large language models outperform humans at estimating society’s everyday norms
This work evaluates six large language models (LLMs) on their ability to estimate American social norms across 555 everyday scenarios and compares these to estimates from 320 humans, indicating that combining a human collective with an LLM substantially outperforms either source alone.
Kimmo Eriksson, Simon Karlsson, I. Vartanova et al.
· Communications AI & Computin... · 1 citation