Knowledge Sanitization of Large Language Models

ACL ARR 2024 August Submission48 Authors

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.

Paper Type: Long

Research Area: Generation

Research Area Keywords: knowledge tracing/discovering/inducing; probing,NLP datasets

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: english

Submission Number: 48