论文精选73°

训练自由任务向量实现LLM行为控制

Training-Free Task Vectors for LLM Behavioral Control

精选理由

新方法TFTVs让LLM行为控制无需微调,支持加法学习减法遗忘,比传统方法更好保留模型能力。

研究人员提出训练自由任务向量(TFTVs)方法,无需微调即可计算类似任务向量的方向。该方法通过前向传播统计信息将激活转向向量映射为秩一权重空间编辑,支持加法学习、减法遗忘和多编辑组合。

正文

在大型语言模型行为控制任务中,TFTVs能持续增强、抑制和组合目标行为,同时保留通用知识和问题解决能力。

原文 · arXiv cs.AI

Training-Free Task Vectors for LLM Behavioral Control

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 forward-pass statistics, while satisfying arithmetic properties that directly support learning via addition, forgetting via subtraction, and the composition of multiple edits. Empirically, we evaluate TFTVs on large language model behavioral control tasks and show that they consistently amplify, suppress, and compose target behaviors while preserving general knowledge and problem-solving skills. We also validate our method against other editing and steering baselines, experimentally demonstrating that TFTVs achieve stronger trait control with better or competitive utility preservation. We hope our work opens new directions for the community in post-training model editing and broader training-free model control. Code is available on the project website: tftv-llm.github.io.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:TFTVs、LLM、任务向量、行为控制,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Gabriel J. Perin, Lucas Boscaini, André Araujo, Nina S. T. Hirata),经 AITOP 多维评分管线结构化提炼。