The Signs Were Always There: Training-Free Detection and Control in Raw Transformer Dimensions

arXiv:2606.12629 · cs.LG, cs.AI · Submitted 2026-06-10 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-06-10

Updated: 2026-10-19

Comments: 40 pages (8-page main text), 6 figures, 39 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AUC — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Closed-Loop Control — 1× in this paper · explained in 3 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks