Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation
Mehdi Jafari, Hao Xue, Flora Salim
Steering large language models typically relies on linear, context-independent interventions in activation space, an assumption that recent work has challenged and that can induce…
cs.CL2026
Mechanistic Indicators of Steering Effectiveness in Large Language Models
Mehdi Jafari, Hao Xue, Flora Salim
Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread u…
cs.CL2026
Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)
Quoc Tuan Pham, Mehdi Jafari, Flora Salim
Test-time compute is central to large reasoning models, yet analysing their reasoning behaviour through generated text is increasingly impractical and unreliable. Response length i…