We study the problem of in-context learning (ICL) with large language mo...
Language models are widely deployed to provide automatic text completion...
Privacy concerns have attracted increasing attention in data-driven prod...
Large pretrained models can be privately fine-tuned to achieve performan...
Recent work has demonstrated the successful extraction of training data ...
Recent papers have shown that large pre-trained language models (LLMs) s...
We give simpler, sparser, and faster algorithms for differentially priva...
In the text processing context, most ML models are built on word embeddi...
Neural language models are known to have a high capacity for memorizatio...
Recent advances in neural network based language models lead to successf...
The large communication cost for exchanging gradients between different ...
Semantic parsing is the problem of deriving machine interpretable meanin...
We consider the probabilistic group testing problem where d random
defec...