arXiv AI July 23, 2026 By Kavin Aravindan, Arihant Rastogi, Aadi Prasad, Krishak Aneja, Saiyam Jain, Vaishnavi Shivkumar, Ponnurangam Kumaraguru

OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

Read the original on arXiv AI →

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.

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 AI

Aug 13

Forecasting Side Effects of Activation Steering

arXiv:2608. 11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining.

By Chong Yong Ong, Alson Wei Jie Sim, Peixin Zhang, Jun Sun

llms safety

arXiv AI

Jun 9

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation

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

llms fine-tuning safety

arXiv AI

Sep 15

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...

By Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen, Zhen Wu, Ashwinee Panda

llms fine-tuning benchmarks safety

arXiv Computation and Language

6d ago

LocUS: Head Selection and Subspace Projection for Targeted Activation Steering

arXiv:2609.31122v1 Announce Type: new Abstract: Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate...

By Irene Tallini, Lorenzo Basile, Valentino Maiorca, Francesco Locatello, Alberto Cazzaniga

llms benchmarks safety

arXiv AI

Jul 3

Safety Targeted Embedding Exploit via Refinement

arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.

By Joshua Adrian Cahyono

llms rag 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

One email a morning, machine-written

Related stories

Forecasting Side Effects of Activation Steering

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

LocUS: Head Selection and Subspace Projection for Targeted Activation Steering

Safety Targeted Embedding Exploit via Refinement

Adversarial Robustness of Activation Steering in Large Language Models