Towards Robust Evaluation of Unlearning in LLMs via Data Transformations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Joshi, Abhinav, Saha, Shaswati, Shukla, Divyaksh, Vema, Sriram, Jhamtani, Harsh, Gaur, Manas, Modi, Ashutosh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929603587604480
author Joshi, Abhinav
Saha, Shaswati
Shukla, Divyaksh
Vema, Sriram
Jhamtani, Harsh
Gaur, Manas
Modi, Ashutosh
author_facet Joshi, Abhinav
Saha, Shaswati
Shukla, Divyaksh
Vema, Sriram
Jhamtani, Harsh
Gaur, Manas
Modi, Ashutosh
contents Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best efforts during the data pre-processing stage while training the LLMs, they may pick some undesirable information such as personally identifiable information (PII). Consequently, in recent times research in the area of Machine Unlearning (MUL) has become active, the main idea is to force LLMs to forget (unlearn) certain information (e.g., PII) without suffering from performance loss on regular tasks. In this work, we examine the robustness of the existing MUL techniques for their ability to enable leakage-proof forgetting in LLMs. In particular, we examine the effect of data transformation on forgetting, i.e., is an unlearned LLM able to recall forgotten information if there is a change in the format of the input? Our findings on the TOFU dataset highlight the necessity of using diverse data formats to quantify unlearning in LLMs more reliably.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15477
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
Joshi, Abhinav
Saha, Shaswati
Shukla, Divyaksh
Vema, Sriram
Jhamtani, Harsh
Gaur, Manas
Modi, Ashutosh
Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best efforts during the data pre-processing stage while training the LLMs, they may pick some undesirable information such as personally identifiable information (PII). Consequently, in recent times research in the area of Machine Unlearning (MUL) has become active, the main idea is to force LLMs to forget (unlearn) certain information (e.g., PII) without suffering from performance loss on regular tasks. In this work, we examine the robustness of the existing MUL techniques for their ability to enable leakage-proof forgetting in LLMs. In particular, we examine the effect of data transformation on forgetting, i.e., is an unlearned LLM able to recall forgotten information if there is a change in the format of the input? Our findings on the TOFU dataset highlight the necessity of using diverse data formats to quantify unlearning in LLMs more reliably.
title Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
topic Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2411.15477