AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection

Ke Sun, Guangsheng Bao, Han Cui, Yue Zhang

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Robust fine-tuning of zero-shot models · 0 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
route each input to a surrogate via DetectRouter instead of fixed LLaMA3-8BFast-DetectGPT · EvoBenchAUROC (%): 81.01 -> 90.85Improved
route each input via DetectRouter instead of fixed surrogateFast-DetectGPT · MAGEAUROC (%): 69.69 -> 77.92Improved
apply routing to Entropy criterionEntropy detector · EvoBenchAUROC (%): 37.46 -> 89.70Improved
apply routing to Likelihood criterionLikelihood detector · EvoBenchAUROC (%): 77.4 -> 81.6Improved
add Stage 2 distributional alignment to Stage 1 prototypes (ablation)DetectRouter · EvoBenchAUROC (%): 72.87 -> 90.85Improved
add Stage 1 prototype construction before Stage 2 (ablation)DetectRouter · EvoBenchAUROC (%): 87.39 -> 90.85Improved
use KL divergence instead of L1 regression (ablation)DetectRouter Stage 2 · EvoBenchAUROC (%): 87.07 -> 90.85Improved
add margin separation loss Lsep (ablation)DetectRouter · MAGEAUROC (%): 74.41 -> 77.92Improved
add prototype anchoring loss (ablation)DetectRouter Stage 2 · EvoBenchAUROC (%): 89.56 -> 90.85Improved
use prototype metric-space routing instead of direct classification (ablation)DetectRouter · MAGEAUROC (%): 75.34 -> 77.92Improved
use LLM2Vec-LLaMA3 encoder instead of RoBERTa-base (ablation)DetectRouter · EvoBenchAUROC (%): 88.34 -> 90.85Improved
take max score over surrogate pool instead of routing (ablation)zero-shot detectors · EvoBenchAUROC (%): 81.01 -> 72.33Hurt

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