Exploring prompts to elicit memorization in masked language model-based named entity recognition

arXiv:2405.03004v1 Announce Type: cross
Abstract: Training data memorization in language models impacts model capability (generalization) and safety (privacy risk). This paper focuses on analyzing prompts' impact on detecting the memorization of 6 masked language model-based named entity recognition models. Specifically, we employ a diverse set of 400 automatically generated prompts, and a pairwise dataset where each pair consists of one person's name from the training set and another name out of the set. A prompt completed with a person's name …

abstract arxiv capability cs.cl cs.lg data diverse impact impacts language language model language models paper privacy prompts recognition risk safety set training training data type