Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4
- https://arxiv.org/abs/2305.00118
- Kent K. Chang, Mackenzie Cramer, Sandeep Soni, David Bamman
GPT, Machine behavior, Training data leakage and memorization in language models
GPT, Machine behavior, Training data leakage and memorization in language models