SheepNav
精选今天0 投票

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

arXiv:2605.05403v1 Announce Type: new Abstract: This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture only overt forms of the phenomenon and leave subtler boundary failures involving epistemic integrity and s

延伸阅读

  1. 邮轮汉坦病毒爆发:你需要知道的关键事实
  2. OpenAI 如何安全运行 Codex:沙箱、审批与原生遥测
  3. AI 倦怠与生育科技:今日下载精选
查看原文