arXiv Artificial Intelligence· Thomas Fel, Matthew Kowal, Matt Feiszli, Satchel Grant, Andrew Lee, Chris Earls, Fatih Dinc, Vasudev Shyam, Usha Bhalla, Leon Bergen, Siddharth Boppana, Ching Fang, Michael Byun, Tristan Gallent, Nicholas Wang, Tal Haklay, Dron Hazra, Neehar Kondapaneni, Connor Watts, Ryan Panwar, Thomas Dooms, Jack Merullo, Atticus Geiger, Ekdeep Singh Lubana, Thomas McGrath, Owen Lewis·· 2 天前AI 评分40
通过内部表征塑造与监控模型：Mechanistic Shaping 框架
Shaping & Monitoring Models through their Internal Representations
AI 导读
研究者提出 Mechanistic Shaping 框架，在训练中通过模型内部表征约束其表达和依赖的概念，在视觉、医学影像、语言等多领域、最高 32B 参数规模及分类、SFT、DPO、GRPO 等训练范式下显著减少目标行为并保持任务性能。
来源：arXiv Artificial Intelligence · arxiv.org