Papers
1–3 of 3Research Paper·Mar 11, 2026
Prism-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge is extracting steering directions that capture the difference between relev...
7.0 viability
Research Paper·Mar 6, 2026
COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods subop...
7.0 viability
Research Paper·Mar 10, 2026
Curveball Steering: The Right Direction To Steer Isn't Always Linear
Activation steering is a widely used approach for controlling large language model (LLM) behavior by intervening on internal representations. Existing methods largely rely on the Linear Representation...
2.0 viability