IBM/RADAR

Code for our NeurIPS2023 accepted paper: RADAR: Robust AI-Text Detection via Adversarial Learning. We tested RADAR on 8 LLMs including Vicuna and LLaMA. The results show that RADAR can attain good detection performance on LLM-generated AI-text while being robust against paraphrasing.

语言：Jupyter Notebook · GitHub 星标：78 · Fork：9

话题：ai-text-detector

在 GitHub 上查看原仓库