Knowledge Sanitization of Large Language Models
This addresses privacy and security issues for LLM users by mitigating memorization of sensitive data, though it is an incremental improvement using existing fine-tuning methods.
The paper tackles privacy concerns in large language models (LLMs) by proposing a knowledge sanitization technique that fine-tunes models using Low-Rank Adaptation (LoRA) to generate harmless responses like 'I don't know' when queried about sensitive information, reducing knowledge leakage while preserving overall model performance.
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.