Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-335
GPT-4's detection performance as a scoring model is highly sensitive to the prompt, varying from 0.7289 to 0.9682 AUROC, far more than GPT-3.5 or Babbage
IC-336
Larger proprietary LLMs (GPT-3.5 175B) are more effective universal text detectors than smaller models (Babbage 1.3B, GPT-Neo-2.7B), contradicting prior findings that smaller models are better
IC-337
GPT-3.5-based detection accuracy drops substantially for Russian text (0.8555 AUROC) compared to near-perfect scores for Urdu, Indonesian, and Arabic, suggesting under-training on Russian