Skip to content
Open access

Large language models outperform humans at estimating society’s everyday norms

Sep 2026 · Communications AI & Computing · Vol 1 · 1 citation · 39 references

TL;DR

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.

Abstract

As AI assistants and social robots enter human environments, their ability to navigate context-dependent social norms is essential to avoid harm and ensure successful collaboration. We evaluate six large language models (LLMs) on their ability to estimate American social norms across 555 everyday scenarios (measured in prior work) and compare these to estimates from 320 humans. LLMs achieve remarkably high accuracy, clearly outperforming the average human. However, the errors LLMs make are systematic; they are similar across runs of the same LLM and even across different LLMs. As a consequence of this homogeneity, aggregating estimates of LLMs produces little improvement. Individual humans make much worse estimates, often defaulting to extreme right-or-wrong judgments even when asked to estimate population averages, but their errors are idiosyncratic and, consequently, aggregating their estimates yields dramatic improvement as these independent errors cancel under averaging. Because humans and LLMs make different errors, combining a human collective with an LLM substantially outperforms either source alone.

Read PDF

Similar papers

Review Sep 2026

Large language models underestimate and partly misrepresent cultural variation in everyday norms

A key aspect of culture is a society's norms about everyday behavior. How accurately do large language models (LLMs) represent cultural differences in such norms? To answer this question we used the recent Global Study of Everyday Norms (GSEN), which collected ratings of 150 scenarios in 90 societies, as the human benc...

Kimmo Eriksson, I. Vartanova, P. Strimling · 0 citations
#artificial intelligence Preprint Oct 2026

PerSo: Investigating Facets of LLMs'Social Intelligence in Real-World Persuasion Scenarios

Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence comprises two aspects: cognitive intelligence, the ability to infer others'mental states, and behavioral intelligence, the abi...

Alieh Zamani, Soroush Esfahanian, Erfan Shahabi et al. · 0 citations
Open access Oct 2026

Large Language Models Predict Human Social Behavior via Interpretable Mechanisms

MindEvolve is introduced, an autonomous workflow designed to predict behavior in social interactions by generating interpretable symbolic models of cognition, and provides a roadmap for advancing LLM-based cognitive modeling toward human-expert-level theory construction.

Ying-Ying Ye, You-Le Fang, Xiao-Xue Gao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.