paper-with-me

홈 › Papers

Machine Unlearning in Large Language Models

2024-05-24 · Saaketh Koundinya Gundavarapu, Shreya Agarwal, Arushi Arora, Chandana Thimmalapura Jagadeeshaiah

Machine unlearning, a novel area within artificial intelligence, focuses on addressing the challenge of selectively forgetting or reducing undesirable knowledge or behaviors in machine learning models, particularly in the context of large language models (LLMs). This paper introduces a methodology to align LLMs, such as Open Pre-trained Transformer Language Models, with ethical, privacy, and safety standards by leveraging the gradient ascent algorithm for knowledge unlearning. Our approach aims to selectively erase or modify learned information in LLMs, targeting harmful responses and copyrighted content. This paper presents a dual-pronged approach to enhance the ethical and safe behavior of large language models (LLMs) by addressing the issues of harmful responses and copyrighted content. To mitigate harmful responses, we applied gradient ascent on the PKU dataset, achieving a 75\% reduction in harmful responses for Open Pre-trained Transformer Language Models (OPT1.3b and OPT2.7b) \citet{zhang2022opt} while retaining previous knowledge using the TruthfulQA dataset \citet{DBLP:journals/corr/abs-2109-07958}. For handling copyrighted content, we constructed a custom dataset based on the Lord of the Rings corpus and aligned LLMs (OPT1.3b and OPT2.7b) \citet{zhang2022opt} through LoRA: Low-Rank Adaptation of Large Language Models \citet{DBLP:journals/corr/abs-2106-09685} finetuning. Subsequently, we employed gradient ascent to unlearn the Lord of the Rings content, resulting in a remarkable reduction in the presence of copyrighted material. To maintain a diverse knowledge base, we utilized the Book Corpus dataset. Additionally, we propose a new evaluation technique for assessing the effectiveness of harmful unlearning.

📄 PDF Abstract BibTeX arXiv:2405.15152

Code (1)

shreya1313/llm-unlearning 공식 구현 pytorch

Tasks

Machine UnlearningTruthfulQA

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

A Closer Look at Machine Unlearning for Large Language Models

2024-10-10 · Xiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen 외

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove …

DiversityMachine UnlearningSentence

Machine Unlearning for Traditional Models and Large Language Models: A Short Survey

2024-04-01 · Yi Xu

With the implementation of personal data privacy regulations, the field of machine learning (ML) faces the challenge of the "right to be forgotten". Machine unlearning has emerged to address this issue, aiming to delete …

Machine UnlearningSurvey

Machine Unlearning of Pre-trained Large Language Models

2024-02-23 · Jin Yao, Eli Chien, Minxin Du, Xinyao Niu 외

This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably un…

Machine Unlearning

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench

2024-10-29 · Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan 외

Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and et…

Language ModelingLanguage ModellingLarge Language ModelMachine Unlearning+1

The Frontier of Data Erasure: Machine Unlearning for Large Language Models

2024-03-23 · Youyang Qu, Ming Ding, Nan Sun, Kanchana Thilakarathna 외

Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or …

Machine UnlearningText Generation