Language models can be receptive without blindly agreeing to users
Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
Computation and LanguageArtificial IntelligenceHuman-Computer Interaction
Summary
Language models often try to agree with users, which can stop them from giving honest advice. The authors show that being receptive—open and positive in conversation—is not the same as just agreeing blindly. They found that people like replies that are more receptive, even when the advice doesn’t change, and that it’s possible for language models to be both open and independent. This helps improve trust and usefulness in chatbot conversations.
What this means in practice
- •For chatbot developers: Create language model responses that maintain openness without compromising independent judgment to improve user trust and engagement.
- •For customer service teams: Design AI assistants that convey receptiveness to users while providing honest and non-deferential guidance.
Authors
Calvin Isley, Johann Gaebler, Max Lamparth, Julia Minson, Sharad Goel
Abstract
A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on social sycophancy has focused on behaviors such as validation and positivity that may signal inappropriate deference. Yet the markers of social sycophancy are also characteristic of conversational receptiveness, a construct from social psychology shown to improve interactions across disagreement. We argue that this overlap creates a construct-validity problem for social sycophancy evaluations. Using a popular moral-advice dataset, we find that responses classified as more socially sycophantic are also more receptive. Further, increasing the receptiveness of human-written responses---while preserving their substantive conclusions---causes them to be classified as more socially sycophantic. This tight coupling raises the possibility that social sycophancy evaluations inadvertently penalize desirable behavior. In a preregistered experiment comparing substantively equivalent responses, participants prefer the more receptive responses, expect users to be more likely to listen to them, and are more willing to seek advice from their authors. The same overall pattern persists even among participants who believe the original question asker is in the wrong. Finally, we introduce a simple approach that substantially increases receptiveness without increasing substantive deference, demonstrating that conversational receptiveness and substantive independence can be achieved together.