用户友好型
计算机科学
业务
人机交互
心理学
互联网隐私
程序设计语言
出处
期刊:
[Association for Computing Machinery]
日期:2026-04-13
卷期号:: 1-15
被引量:82
标识
DOI:10.1145/3772318.3791079
摘要
LLM-powered conversational agents are increasingly influencing our decision-making, raising concerns about “sycophancy”–the tendency for LLMs to excessively agree with users even at the expense of truthfulness. While prior work has primarily examined LLM sycophancy as a model behavior, our understanding of how users perceive this phenomenon and its impact on user trust remains significantly lacking. In this work, we conceptualize LLM sycophancy along two key constructs: conversational demeanor (complimentary vs. neutral) and stance adaptation (adaptive vs. consistent). A 2 × 2 between-subjects experiment (N = 224) revealed complex dynamics: complimentary LLMs that adapted their stance reduced perceived authenticity and trust, while neutral LLMs that adapted enhanced both, suggesting a pathway for manipulating users into over-trusting LLMs beyond their actual capabilities. Our findings advance user-centric understanding of LLM sycophancy and provide profound implications for developing more ethical and trustworthy LLM systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI