Large Language Models are as persuasive as humans, but why? About the cognitive effort and moral-emotional language of LLM arguments

arXiv:2404.09329v1 Announce Type: new
Abstract: Large Language Models (LLMs) are already as persuasive as humans. However, we know very little about why. This paper investigates the persuasion strategies of LLMs, comparing them with human-generated arguments. Using a dataset of 1,251 participants in an experiment, we analyze the persuaion strategies of LLM-generated and human-generated arguments using measures of cognitive effort (lexical and grammatical complexity) and moral-emotional language (sentiment and moral analysis). The study reveals that LLMs produce arguments that require higher …

abstract arxiv cognitive cs.cl dataset generated however human humans language language models large language large language models llm llms paper persuasion strategies them type