The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Summary
This paper introduces geometric stability measures—based on pairwise distance consistency in representations—to predict language model steerability and detect structural drift. Supervised variants achieve near-perfect correlation (ρ=0.89-0.97) with linear steerability across 35-69 embedding models, while unsupervised variants outperform CKA and Procrustes for post-deployment drift detection.
View Cached Full Text
Cached at: 04/21/26, 07:21 AM
Paper page - The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Source: https://huggingface.co/papers/2604.17698
Abstract
Geometric stability measures predict language model controllability and detect structural degradation, with supervised variants excelling at steering prediction and unsupervised variants at drift detection.
Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure degrades. We show thatgeometric stability, the consistency of a representation’s pairwise distance structure, addresses both.Supervised Shesha variantsthat measuretask-aligned geometric stabilitypredictlinear steerabilitywith near-perfect accuracy (ρ= 0.89-0.97) across 35-69 embedding models and three NLP tasks, capturing unique variance beyond class separability (partial ρ= 0.62-0.76). A critical dissociation emerges:unsupervised stabilityfails entirely for steering on real-world tasks (ρapprox 0.10), revealing that task alignment is essential for controllability prediction. However,unsupervised stabilityexcels atdrift detection, measuring nearly 2times greater geometric change thanCKAduring post-training alignment (up to 5.23times in Llama) while providing earlier warning in 73\% of models and maintaining a 6times lower false alarm rate thanProcrustes. Together, supervised andunsupervised stabilityform complementary diagnostics for theLLM deployment lifecycle: one for pre-deployment controllability assessment, the other for post-deployment monitoring.
View arXiv pageView PDFGitHub0Add to collection
Get this paper in your agent:
hf papers read 2604\.17698
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper1
#### pcr2120/shesha-geometry Other• Updatedabout 5 hours ago
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2604.17698 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2604.17698 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
This paper investigates the geometric relationship between directions in language model activations that detect a behavior versus those that control it, finding that for hallucination detection they are nearly orthogonal (cosine ~0.12), while for output format they align perfectly, challenging a common assumption in mechanistic interpretability.
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
This paper proposes using steering vectors for control over language model behavior and latent space-based calibrators to assess trustworthiness, aiming to demystify internal representations and build more reliable AI systems.
Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems
This paper investigates semantic context drift in reasoning-class LLMs within hybrid decision support systems, proposing a mathematical model and a stability metric. A two-month experiment reveals latent goal-targeting drift and formulates engineering recommendations for control stability.
Controlling Tool Use with Heading-Specific Activation Steering
This paper investigates whether tool-use decisions in large language models have stable internal representations that can be extracted and manipulated via activation steering, demonstrating that heading-specific steering vectors can suppress unnecessary tool use across five open-source models and three domains. The geometric analysis reveals that tool-invocation steps exhibit diffuse, bimodal alignment rather than the clean linear structure expected for parametrically grounded concepts.
Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence
This paper introduces geometric stability as a measure of how reliably pairwise stimulus distances reproduce across trials, demonstrating its behavioral relevance and circuit dependence across brain regions, with an attractor network model explaining its emergence.