Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936
-
Updated
Jun 10, 2024 - Python
Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936
A new method for recognizing text that is included in an LLM's training data.
Add a description, image, and links to the pretraining-data-detection topic page so that developers can more easily learn about it.
To associate your repository with the pretraining-data-detection topic, visit your repo's landing page and select "manage topics."