Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
Geometry-Lite is a compact prompt-level safety probe that analyzes how large language models distinguish safe from unsafe prompts across layers. It reveals that safety evidence is primarily a persistent layer-wise margin geometry rather than a layer-to-layer motion signal, and it provides interpretable insights into low-false-positive decisions and benchmark shift robustness.
[2605.20241] Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
[Submitted on 18 May 2026]
Title:Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
View a PDF of the paper titled Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry, by Woo Seob Sim and 1 other authors
View PDF HTML (experimental)
Abstract:Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detection performance does not explain the geometry of this separation. In particular, it remains unclear how safety evidence is formed across layers, which aspects of that layer-wise geometry support low-false-positive decisions, and which geometric biases remain stable under benchmark shift. We study this as an empirical decomposition problem and introduce Geometry-Lite, a compact prompt-level probe that maps each layer's final prompt-token representation to signed margins under centroid, local-neighborhood, and supervised linear-boundary readouts, then summarizes the resulting margin profiles by boundary position, layer-to-layer change, and coarse shape. Across nine instruction-tuned backbones ($1.2$B--$70$B) and seven safety benchmarks, Geometry-Lite improves over single-layer probes while remaining close to raw multi-layer score stacking, making it a useful instrument for analyzing the multi-layer safety signal. The decomposition shows that safety evidence is expressed primarily through persistent boundary-position geometry: final or extremal margins and unsafe-side layer occupancy dominate aggregate detection performance. In contrast, finite-difference drift and structural summaries add little to pooled AUROC, although drift can provide small recall-oriented corrections under shifted low-FPR thresholds. Under benchmark shift, optimized linear boundaries are sharp on the training mixture, whereas class-conditional mean geometry retains separation more reliably on a predefined hard held-out subset. Overall, prompt-level safety evidence is not primarily a layer-to-layer motion signal, but a persistent layer-wise margin geometry whose useful components and readout-level biases become visible in decision-critical regimes.
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2605.20241 [cs.LG]
(or arXiv:2605.20241v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.20241
arXiv-issued DOI via DataCite
Submission history
From: Woo Seob Sim [view email] [v1] Mon, 18 May 2026 00:12:24 UTC (127 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry, by Woo Seob Sim and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)