NEWS
Study: Large language models cannot distinguish social normsThe study shows that while large language models (LLMs) are successful at mimicking behaviors, they fail to selectively learn norms enforced by social sanctions. By blindly copying meaningless behaviors alongside mandatory rules, the models prove they lack normative competence. This is a news summary compiled for the AiPulse newsletter — not the original article. The original article is at arxiv.org. Read the original article AI Critique → English (automatic translation) |