Query-Adaptive Neuron Steering for LLMs

arXiv:2610.14519 · cs.LG, cs.CL · Submitted 2026-10-10 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/YanxiP/Q-NeuS

Terminology

• Steering — 1× in this paper · explained in 2 episodes

Sources

• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Proximal Policy Optimization Algorithms
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• Ministral 3
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Training Verifiers to Solve Math Word Problems
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• LoRA: Low-Rank Adaptation of Large Language Models

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