arXiv AI September 10, 2026 By Gabriel J. Perin, Lucas Boscaini, Andr\'e Araujo, Nina S. T. Hirata

Training-Free Task Vectors for LLM Behavioral Control

The paper introduces Training-Free Task Vectors (TFTVs), a method for computing task-vector-like directions in large language models without fine‑tuning. TFTVs map activation steering vectors to rank‑one weight‑space edits using only forward‑pass statistics, enabling arithmetic operations such as learning, forgetting, and composing edits. Experiments show that TFTVs consistently amplify, suppress, and combine target behaviors while preserving general knowledge, outperforming other editing and steering baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 15

Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.

By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u

llms efficiency safety

arXiv AI

Jun 24

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

arXiv:2511. 20892v4 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect or outdated content after being employed.

By Xuyuan Liu, Shengyu Chen, Xinshuai Dong, Yanchi Liu, Xujiang Zhao, Haoyu Wang, Yujun Yan, Haifeng Chen, Zhengzhang Chen

llms benchmarks

arXiv Machine Learning

Jun 2

Controllable Value Alignment in Large Language Models through Neuron-Level Editing

arXiv:2602. 07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands.

By Yonghui Yang, Yihui Wang, Junwei Li, Jilong Liu, Fengbin Zhu, Weibiao Huang, Le Wu, Richang Hong, Tat-Seng Chua

llms safety

arXiv Machine Learning

Jun 11

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models

arXiv:2606. 11206v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization.

By Yucheng Zhou, Junwei Sheng, Qianning Wang, Jianbing Shen

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Sep 1

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

arXiv:2608.31096v1 Announce Type: cross Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...

By Yunxiang Fu, Meng Lou, Yizhou Yu

fine-tuning

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

One email a morning, machine-written

Related stories

Inference-Time Machine Unlearning via Gated Activation Redirection

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

Controllable Value Alignment in Large Language Models through Neuron-Level Editing

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs