Controllable Memorization in LLMs via Weight Pruning
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 15141-15156
Abstract
Chenjie Ni, Zhepeng Wang, Runxue Bao, Shangqian Gao, Yanfu Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.Keywords
This publication has 5 references indexed in Scilit:
- Unlocking Memorization in Large Language Models with Dynamic Soft Prompting2024
- Machine Unlearning of Pre-trained Large Language Models2024
- Copyright Violations and Large Language Models2023
- Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning2023
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019