The Low-Rank Alignment Control Surface

Geometry

What the low-rank alignment control surface looks like.

Preference / alignment post-training concentrates its weight update. Measured by stable rank‖ΔW‖_F² / ‖ΔW‖₂², a soft, continuous count of effective directions — the update to the attention QKV projection is low and, strikingly, flat: it does not grow with model width.

A task-intrinsic stable-rank floor

The lazy-rudder study trains DPO LoRA adapters across a width sweep and finds the QKV-update stable rank sits at a low constant — the task-intrinsic floor ≈ 3.65 on the GPT-NeoX (Pythia) family. The rank is set by the preference-learning task, not by parameter count.

It replicates across architecture (LRS1)

LRS1 re-measures the floor on Qwen2.5 — a Llama-style architecture (split q/k/v projections, grouped-query attention, gated SwiGLU). The floor holds:

Modeld_modelQKV stable rank
Qwen2.5-0.5B8963.4351
Qwen2.5-1.5B15363.9625
Qwen2.5-3B20483.9387

Across a 4× width range the stable rank stays inside a spread of just 0.5274 — verdict REPLICATES_FLAT_FLOOR. The Qwen2.5 floor agrees with the Pythia reference to within ≈ 0.13. The low-rank alignment control surface is architecture-robust and scale-invariant.

That is the geometry. The natural next question — answered on the Function page — is what a surface this compact actually does.

Source: cross-check/preregistry/lrs1_srank_scaling_qwen25_2026-05-17/; the lazy-rudder paper for the Pythia sweep.