paper-with-me

홈 › Papers

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

2024-09-20 · Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, yanfu Zhang

Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize training data, leading to potential privacy breaches and copyright infringement. Accurate measurement of this memorization is essential to evaluate and mitigate these potential risks. However, previous attempts to characterize memorization are constrained by either using prefixes only or by prepending a constant soft prompt to the prefixes, which cannot react to changes in input. To address this challenge, we propose a novel method for estimating LLM memorization using dynamic, prefix-dependent soft prompts. Our approach involves training a transformer-based generator to produce soft prompts that adapt to changes in input, thereby enabling more accurate extraction of memorized data. Our method not only addresses the limitations of previous methods but also demonstrates superior performance in diverse experimental settings compared to state-of-the-art techniques. In particular, our method can achieve the maximum relative improvement of 112.75% and 32.26% over the vanilla baseline in terms of discoverable memorization rate for the text generation task and code generation task respectively.

📄 PDF Abstract BibTeX arXiv:2409.13853

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationMemorizationQuestion AnsweringText Generation

Similar Papers 제목 키워드 기반

Memorization Dynamics in Knowledge Distillation for Language Models

2026-01-21 · Jaydeep Borkar, Karan Chadha, Niloofar Mireshghallah, Yuchen Zhang 외 arxiv

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tu…

Knowledge Distillation

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

2022-05-22 · Kushal Tirumala, Aram H. Markosyan, Luke Zettlemoyer, Armen Aghajanyan

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across …

Language ModelingLanguage ModellingMasked Language ModelingMemorization

Soft Label Memorization-Generalization for Natural Language Inference

2017-02-27 · John P. Lalor, Hao Wu, Hong Yu

Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for. It has been shown that this disagreement can be considered signal instead of nois…

MemorizationNatural Language Inference

A Multi-Perspective Analysis of Memorization in Large Language Models

2024-05-19 · Bowen Chen, Namgi Han, Yusuke Miyao

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some spec…

Memorization

The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization

2024-08-29 · Luka Borec, Philipp Sadler, David Schlangen

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as mon…

DiagnosticMemorizationText Generation