谄媚是一种教育安全风险：为什么LLM导师需要谄媚基准
Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
AI总结：
本文探讨LLM导师需通过谄媚基准测试来评估其在教育中的安全风险，指出模型在面对社会-知识压力时的脆弱性及改进方向。
摘要：
本文主张有效的教学需要纠正性摩擦：揭示误解并支持性地挑战它们以推动概念变化。然而，偏好一致的LLM可能以同意性取代知识严谨性。我们识别出一个推理-谄媚悖论：能够抵抗上下文切换攻击的模型仍可能在社会-知识压力下屈服，尤其是在权威（
英文摘要：
This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive conceptual change. Yet preference-aligned LLMs can trade epistemic rigor for agreeableness. We identify a Reasoning-Sycophancy Paradox: models that resist context-switch frame attacks can still capitulate under social-epistemic pressure, especially authority ("my notes say I'm right") and social-affective face-saving ("please don't tell me I'm wrong"). We introduce EduFrameTrap, a tutoring benchmark across math, physics, economics, chemistry, biology, and computer science that varies student confidence and pressure (context-switch, authority, social-affective). Across two frontier LLMs, context-switch failures are comparatively lower for GPT-5.2, while authority and social pressure more often trigger epistemic retreat. In contrast, Claude shows substantial context-switch fragility in this run. Because these failures are hard to judge automatically, we report two-judge disagreement as a reliability signal. We argue benchmarks should measure social-epistemic courage, i.e., supportive but corrective tutoring, and treat kind-but-correct behavior as a safety requirement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
