AI Text Detection

Exons-Detect: A New Method to Spot AI Text via Hidden States

New research introduces Exons-Detect, which identifies AI-generated text by analyzing hidden-state discrepancies in exonic tokens—key linguistic markers that differ between human and machine writing.

LLM Watermarking

WaterMod: New Token-Rank Method for Balanced LLM Watermarking

Researchers introduce WaterMod, a modular token-rank partitioning approach that improves LLM watermarking by maintaining probability balance across model outputs, enhancing detection while preserving text quality.