AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Every Language Model Has a Forgery-Resistant Signature

Matthew Finlayson, Xiang Ren, Swabha Swayamdipta

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ellipse-specific fitting instead of SVD-based quadric fitting (ablation)ellipse extraction · small LMs with epsilon smoothingvalidity of recovered ellipseImproved
fit the ellipse with more output samples (ablation)ellipse extraction · 1M-parameter model, bias/stretch/rotation errordistance to true parametersImproved
increase model size (hidden dimension) (ablation)ellipse fitting under epsilon smoothing · GPT NeoX d=64 vs Llama 3 d=4096hidden-state norm concentration near 1Improved
compare logprobs against the generating model's ellipse versus other models' ellipsesellipse signature · Olmo 2 7B, Llama 3.1, Qwen 3 8B, gpt ossmean distance to ellipse: generating model has smallest distance by several orders of magnitudeImproved
apply GPU acceleration to ellipse fittingellipse extraction · large modelsfeasibilityNo clear effect
apply approximation methods to speed up ellipse fittingellipse extraction · ellipse fitting accuracyparameter accuracyHurt
apply temperature scaling to logitsellipse signature detection · logit transformationsdetectabilityNo clear effect
apply top-k truncation with k<dellipse signature detection · logit transformationsusefulness of signatureHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy