Recovering from Privacy-Preserving Masking with Large Language Models. (arXiv:2309.08628v3 [cs.CL] UPDATED)

Model adaptation is crucial to handle the discrepancy between proxy training
data and actual users data received. To effectively perform adaptation, textual
data of users is typically stored on servers or their local devices, where
downstream natural language processing (NLP) models can be directly trained
using such in-domain data. However, this might raise privacy and security
concerns due to the extra risks of exposing user information to adversaries.
Replacing identifying information in textual data with a generic marker has
been …

data devices domain effectively language language models large local masking natural natural language natural language processing nlp privacy proxy servers training training data