Copertina

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Jiawei, Zhou, Doudou
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
di: Koh, Seunghee, et al.
Pubblicazione: (2026)

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
di: Wan, Yixin, et al.
Pubblicazione: (2025)

Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
di: Lee, Hwiyeong, et al.
Pubblicazione: (2025)

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
di: Niu, Peizhi, et al.
Pubblicazione: (2025)

UniErase: Towards Balanced and Precise Unlearning in Language Models
di: Yu, Miao, et al.
Pubblicazione: (2025)

Evaluating Deep Unlearning in Large Language Models
di: Wu, Ruihan, et al.
Pubblicazione: (2024)

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
di: Chang, Hwan, et al.
Pubblicazione: (2025)

Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
di: Tang, Haoyu, et al.
Pubblicazione: (2024)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
di: Kadhe, Swanand Ravindra, et al.
Pubblicazione: (2024)

CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept
di: Wu, YuXuan, et al.
Pubblicazione: (2024)

Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models
di: Chen, Haokun, et al.
Pubblicazione: (2025)

Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis
di: Ma, Weitao, et al.
Pubblicazione: (2024)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
di: Jiang, Peihai, et al.
Pubblicazione: (2025)

Offset Unlearning for Large Language Models
di: Huang, James Y., et al.
Pubblicazione: (2024)

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
di: Lin, Yujie, et al.
Pubblicazione: (2026)

Unlearning Climate Misinformation in Large Language Models
di: Fore, Michael, et al.
Pubblicazione: (2024)

A Survey on Unlearning in Large Language Models
di: Qiu, Ruichen, et al.
Pubblicazione: (2025)

Large Language Model Unlearning
di: Yao, Yuanshun, et al.
Pubblicazione: (2023)

Deep Contrastive Unlearning for Language Models
di: He, Estrid, et al.
Pubblicazione: (2025)

Machine Unlearning in Large Language Models
di: Gundavarapu, Saaketh Koundinya, et al.
Pubblicazione: (2024)

Soft Prompting for Unlearning in Large Language Models
di: Bhaila, Karuna, et al.
Pubblicazione: (2024)

Investigating Model Editing for Unlearning in Large Language Models
di: Hossain, Shariqah, et al.
Pubblicazione: (2025)

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
di: Choi, Minseok, et al.
Pubblicazione: (2024)

Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
di: Gu, Kang, et al.
Pubblicazione: (2024)

Model Unlearning Objectives Vary for Distinct Language Functions
di: Atil, Berk, et al.
Pubblicazione: (2026)

Evaluating Cross-Lingual Unlearning in Multilingual Language Models
di: Lizzo, Tyler, et al.
Pubblicazione: (2026)

Mitigating Biases in Language Models via Bias Unlearning
di: Liu, Dianqing, et al.
Pubblicazione: (2025)

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
di: Tran, Toan, et al.
Pubblicazione: (2025)

Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
di: Lee, Hong kyu, et al.
Pubblicazione: (2025)

Exclusive Unlearning
di: Sasaki, Mutsumi, et al.
Pubblicazione: (2026)

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
di: Yang, Zhengbang, et al.
Pubblicazione: (2026)

Understanding the Dilemma of Unlearning for Large Language Models
di: Zhang, Qingjie, et al.
Pubblicazione: (2025)

Rethinking Machine Unlearning for Large Language Models
di: Liu, Sijia, et al.
Pubblicazione: (2024)

Learning and Unlearning of Fabricated Knowledge in Language Models
di: Sun, Chen, et al.
Pubblicazione: (2024)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
di: Spohn, Philipp, et al.
Pubblicazione: (2025)

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
di: Doshi, Jai, et al.
Pubblicazione: (2024)

Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation
di: Li, Zizhong, et al.
Pubblicazione: (2025)

Guardrail Baselines for Unlearning in LLMs
di: Thaker, Pratiksha, et al.
Pubblicazione: (2024)

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
di: Muhamed, Aashiq, et al.
Pubblicazione: (2025)

Towards Safer Large Language Models through Machine Unlearning
di: Liu, Zheyuan, et al.
Pubblicazione: (2024)