Back to Search Start Over

Knowledge Sanitization of Large Language Models

Authors :
Ishibashi, Yoichi
Shimodaira, Hidetoshi
Ishibashi, Yoichi
Shimodaira, Hidetoshi
Publication Year :
2023

Abstract

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential information, raising critical security concerns. Our technique efficiently fine-tunes these models using the Low-Rank Adaptation (LoRA) method, prompting them to generate harmless responses such as ``I don't know'' when queried about specific information. Experimental results in a closed-book question-answering task show that our straightforward method not only minimizes particular knowledge leakage but also preserves the overall performance of LLMs. These two advantages strengthen the defense against extraction attacks and reduces the emission of harmful content such as hallucinations.

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1438480962
Document Type :
Electronic Resource