Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

arXiv:2604.03867 · cs.LG · Submitted 2026-04-04 · Read on arXiv

cs.LG

Submitted: 2026-04-04

Updated: 2026-10-15

Terminology

• Steering — 7× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 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