Shaping & Monitoring Models through their Internal Representations
arXiv:2611.07071v1 Announce Type: new Abstract: We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations. Mechanistic Shaping is applied during training so that models follow specifications (rules) about which concepts they express, measured via their outputs or internal representations (e.g., no harmful content), and also which concepts they rely on, i.e., what they use to make their decisions (e.g., not a candidate's gender when screening a r\'esum\'e). Across multiple domains (vision, medical imaging, language), scales (up to 32B paramete
阅读原文 · arXiv 机器学习本文由 SoccerDream AI 自动聚合索引，内容版权归原作者与 arXiv 机器学习 所有。
本站仅作技术动态聚合，不构成任何形式的建议。
本站仅作技术动态聚合，不构成任何形式的建议。