1
False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs
论文提出LLMs中“虚假不动点”现象，揭示模型在自我反馈循环中错误强化导致稳定失校准，并引入表征压缩机制提供新解释。
arXiv:2510.14925v4 Announce Type: replace Abstract: High-confidence errors in large language models are often treated as fragile failures. We study an…