# EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors

arXiv: https://arxiv.org/abs/2610.09976 · HTML: https://mlsanity.com/paper/2610.09976/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 6 of its 31 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Ministral 3](https://mlsanity.com/paper/2601.08584/) (2026)
- [Evade ChatGPT Detectors via A Single Space](https://mlsanity.com/paper/2307.02599/) (2023)

## Abstract (arXiv)

AI-generated text (AIGT) detection can be sensitive to the decoding choices of the source large language model (LLM). We observe that perturbing next-token logits or adjusting sampling temperature can reduce detection performance, providing a clear signal of detector vulnerability to decoding-time distribution changes. Building on this observation, we propose EASE (Entropy-Adaptive Distribution Shaping for Evasion), a training-free and detector-agnostic framework for evading AIGT detectors. EASE computes predictive entropy directly from the source LLM's next-token distribution and uses it to adapt both logit perturbation and sampling temperature, without detector feedback or model fine-tuning. Experiments across three source LLMs and multiple detectors demonstrate consistent reductions in detection performance, with negligible degradation in text quality and negligible inference overhead.