arXiv Machine Learning August 11, 2026 By Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Jonathan May

ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation

Read the original on arXiv Machine Learning →

arXiv:2606. 22357v2 Announce Type: replace-cross Abstract: Language models are widely used in assistant settings, where controlling behavioral attributes is often essential.

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 Machine Learning.

arXiv AI

Jul 13

Multi-Attribute Steering of Language Models via Targeted Intervention

arXiv:2502. 12446v3 Announce Type: replace-cross Abstract: Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.

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

llms nlp fine-tuning efficiency safety

arXiv Computation and Language

Sep 22

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...

By Jiaqian Li, Yanshu Li, Kuan-Hao Huang

llms fine-tuning

arXiv AI

Sep 10

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.

By Gabriel J. Perin, Lucas Boscaini, Andr\'e Araujo, Nina S. T. Hirata

llms fine-tuning

arXiv AI

Sep 10

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...

By Mohammad Mahdi Abootorabi, Armin Saghafian, Ali Bazshoushtari, Hamid Rezaei, EunJeong Hwang, Vered Shwartz, Parvin Mousavi, Purang Abolmaesumi

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 7

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

arXiv:2509. 25533v2 Announce Type: replace-cross Abstract: As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important.

By Ravikumar Balakrishnan, Mansi Phute

llms multimodal benchmarks safety

arXiv AI

Jul 23

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

arXiv:2607. 19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection.

By Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan

llms fine-tuning

One email a morning, machine-written

Related stories

Multi-Attribute Steering of Language Models via Targeted Intervention

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

Training-Free Task Vectors for LLM Behavioral Control

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models