SOURCE-LINKED INTELLIGENCE

Training-Free Task Vectors for LLM Behavioral Control

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Task vectors enable post-training model editing by identifying semantically meaningful directions in weight space, typically computed as the difference between a fine-tuned model and its pretrained initialization. However, this reliance on fine-tuning makes discovering such directions costly and limits the practicality of post-training model editing. To address this limitation, we introduce Training-Free Task Vectors (TFTVs), a novel method to compute task-vector-like directions without requiring fine-tuning. Our method maps activation steering vectors to rank-one weight-space edits using only

Read original source ↗ Open in workspace

recordType

paper

region

Global