MetaSteer is a new method for steering large language models that learns nonlinear, context-dependent interventions applied to attention projection matrices. Unlike traditional linear, context-independent techniques, MetaSteer adapts its effects based on the input, requiring no linear concept-geometry assumption. Trained once on a pooled preference corpus, it transfers zero‑shot to unseen concepts and out‑of‑distribution contexts, matching or surpassing strong task‑specific baselines on multiple benchmarks and model families.
By Mehdi Jafari, Hao Xue, Flora Salim
arXiv:2609.14151v1 Announce Type: cross
Abstract: Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model b...
By Prajjwal Bhattarai, Tuka Alhanai
arXiv:2606. 15092v1 Announce Type: new Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs).
By Minh-Hieu Pham, Bach Do, Laziz Abdullaev, Tan Minh Nguyen, Khoat Than
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
By Tuc Nguyen, Thai Le
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
arXiv:2602. 00945v2 Announce Type: replace-cross Abstract: LLMs are multilingual by training, yet their lingua franca is often English, reflecting English language dominance in pretraining.
By Anusa Saha, Tanmay Joshi, Vinija Jain, Aman Chadha, Amitava Das
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
arXiv:2607. 19806v1 Announce Type: cross Abstract: Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vectors may weaken safety behavior, while refusal vectors may induce over-refusal on benign prompts.
By Kavin Aravindan, Arihant Rastogi, Aadi Prasad, Krishak Aneja, Saiyam Jain, Vaishnavi Shivkumar, Ponnurangam Kumaraguru
arXiv:2603. 02237v2 Announce Type: replace-cross Abstract: Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal activations at inference time.
By Laziz U. Abdullaev, Noelle Y. L. Wong, Ryan T. Z. Lee, Shiqi Jiang, Khoi N. M. Nguyen, Tan M. Nguyen
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
By Qi Cao, Jian Lou, Meiting Liu, Wenjie Feng, Dan Li, See-Kiong Ng, Anh Tuan Luu
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
By Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal, Dipesh Mahato
arXiv:2608. 10260v1 Announce Type: new Abstract: Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network.
By Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson, Daniel McKenzie, Kyle Chard, Ian Foster