appliedml42
@appliedml42
Bag of Tricks for Training Data Extraction from Language Models abs:https://arxiv.org/abs/2302.04460v1 https://i.imgur.com/MT3TcVP.png
1 reply
0 recast
0 reaction
appliedml42
@appliedml42
This paper proposes tricks for improving training data extraction from language models, such as sampling strategies and token-level criteria. Experiments show that these tricks can significantly outperform the baseline in most cases, providing a stronger baseline for future research.
1 reply
0 recast
0 reaction
