arXiv Machine Learning June 15, 2026 By Yuntai Bao, Qinfeng Li, Xinyan Yu, Ge Su, Wenqi Zhang, Liu Yan, Haiqin Weng, Jianwei Yin, Xuhong Zhang

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

Read the original on arXiv Machine Learning →

arXiv:2605. 05983v2 Announce Type: replace Abstract: Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 11

When is Your LLM Steerable?

arXiv:2606. 11599v1 Announce Type: cross Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration.

By Chenrui Fan, Yize Cheng, Ming Li, Soheil Feizi, Tianyi Zhou

llms

Hugging Face Trending Papers

Jun 10

When is Your LLM Steerable?

Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Finding the regime and boundaries of successful steering typically requires expensive grid searches and post-hoc evaluation of full autoregressive rollouts.

llms

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 Machine Learning

Jul 9

Towards Understanding Steering Strength

arXiv:2602. 02712v2 Announce Type: replace Abstract: A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations.

By Magamed Taimeskhanov, Samuel Vaiter, Damien Garreau

llms

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

arXiv AI

Jun 9

Adversarial Robustness of Activation Steering in Large Language Models

arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.

By Kien Le, Thai Le

llms safety

Related stories

When is Your LLM Steerable?

When is Your LLM Steerable?

Multi-Attribute Steering of Language Models via Targeted Intervention

Towards Understanding Steering Strength

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

Adversarial Robustness of Activation Steering in Large Language Models