Large Language Models and Conversational Counter-Arguments to Anti-Public Sector Bias

Abstract

Can a good argument change an individual’s mind? In three pre-registered experiments, we explore this question in the domain of public sector organizational performance. We observe human subjects as they engage in conversations with a generative artificial intelligence (AI) programmed to argue in one of seven distinct “styles,” including a confrontational challenger style, a didactic style, and a sycophantic style. We develop a theory of effective argumentation predicting that conversational styles which are pleasant and engaging will be more persuasive than styles which are unpleasant or unstimulating. Contrary to this prediction, we find that conversational styles which challenge subjects’ negative views of government agencies produce significant positive attitude change, while sycophantic styles that indulge those views do not. Troublingly, subjects find the sycophantic styles more enjoyable, less frustrating, and more credible than the challenger styles. This dissociation between user experience and persuasive outcome—what we call “grudging persuasion”—suggests that attitude change does not require a pleasant conversational experience, and that the styles subjects enjoy most may be precisely the ones least likely to move them. Our findings point to a potentially dark side of LLM-based persuasion: sycophantic styles that users find most appealing are the least effective at correcting misinformed views.