Intrinsic Test of Unlearning Using Parametric Knowledge Traces
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 19524-19546
Abstract
Yihuai Hong, Lei Yu, Haiqin Yang, Shauli Ravfogel, Mor Geva. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Jailbreak and Guard Aligned Language Models With Only Few In-Context DemonstrationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
- Rethinking machine unlearning for large language modelsNature Machine Intelligence, 2025
- Evaluating the Ripple Effects of Knowledge Editing in Language ModelsTransactions of the Association for Computational Linguistics, 2024
- A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis2023
- Analyzing Transformers in Embedding Space2023
- What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary2023
- Knowledge Unlearning for Mitigating Privacy Risks in Language Models2023
- Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space2022
- LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models2022
- Transformer Feed-Forward Layers Are Key-Value Memories2021