0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag
"The paper introduces a technique called LoReFT (Low-rank Linear Subspace ReFT). Similar to LoRA (Low Rank Adaptation), it uses low-rank approximations to intervene on hidden representations. It shows that linear subspaces contain rich semantics that can be manipulated to steer model behaviors."
First / Previous / Next / Last / Page 1 of 0