PRIVACY-PRESERVING IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS

doi:doi:10.57702/cl2387qy

PRIVACY-PRESERVING IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS

In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby improving accuracy and relevance. However, LLM’s responses may leak the sensitive private information contained in in-context exemplars. To address this challenge, we propose Differentially Private In-context Learning (DP-ICL), a general paradigm for privatizing ICL tasks.

BibTex:

@dataset{Tong_Wu_and_Ashwinee_Panda_and_Jiachen_T_Wang_and_Prateek_Mittal_2024,
    abstract = {In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby improving accuracy and relevance. However, LLM’s responses may leak the sensitive private information contained in in-context exemplars. To address this challenge, we propose Differentially Private In-context Learning (DP-ICL), a general paradigm for privatizing ICL tasks.},
    author = {Tong Wu and Ashwinee Panda and Jiachen T. Wang and Prateek Mittal},
    doi = {10.57702/cl2387qy},
    institution = {No Organization},
    keyword = {'Large Language Models', 'differential privacy', 'in-context learning'},
    month = {dec},
    publisher = {TIB},
    title = {PRIVACY-PRESERVING IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS},
    url = {https://service.tib.eu/ldmservice/dataset/privacy-preserving-in-context-learning-for-large-language-models},
    year = {2024}
}