How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

arXiv:2604.04385 · cs.CL, cs.AI, cs.LG · Submitted 2026-04-06 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-04-06

Updated: 2026-10-20

Comments: Code and data: https://github.com/gregfrank/how-alignment-routes. Accepted at the Mechanistic Interpretability Workshop at the 43rd International Conference on Machine Learning (ICML), 2026

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

Terminology

• Ablation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering