Copertina

Per-parameter Task Arithmetic for Unlearning in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cai, Chengyi, Ye, Zesheng, Yao, Jiangchao, Qi, Jianzhong, Han, Bo, Zhang, Xiaolu, Liu, Feng, Zhou, Jun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning
di: Cai, Chengyi, et al.
Pubblicazione: (2026)

Attribute-based Visual Reprogramming for Vision-Language Models
di: Cai, Chengyi, et al.
Pubblicazione: (2025)

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
di: Cai, Chengyi, et al.
Pubblicazione: (2025)

Bayesian-guided Label Mapping for Visual Reprogramming
di: Cai, Chengyi, et al.
Pubblicazione: (2024)

Sample-specific Masks for Visual Reprogramming-based Prompting
di: Cai, Chengyi, et al.
Pubblicazione: (2024)

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction
di: Ye, Zesheng, et al.
Pubblicazione: (2025)

DeepInception: Hypnotize Large Language Model to Be Jailbreaker
di: Li, Xuan, et al.
Pubblicazione: (2023)

Towards Understanding Valuable Preference Data for Large Language Model Alignment
di: Zhang, Zizhuo, et al.
Pubblicazione: (2025)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
di: Zhou, Zhanke, et al.
Pubblicazione: (2025)

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

Decoupling the Class Label and the Target Concept in Machine Unlearning
di: Zhu, Jianing, et al.
Pubblicazione: (2024)

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
di: Zhou, Zhanke, et al.
Pubblicazione: (2024)

Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
di: Zhang, Zizhuo, et al.
Pubblicazione: (2025)

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
di: Yu, Geng, et al.
Pubblicazione: (2024)

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

Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models
di: Sun, Yuhao, et al.
Pubblicazione: (2026)

Deterministic Differentiable Structured Pruning for Large Language Models
di: Huang, Weiyu, et al.
Pubblicazione: (2026)

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
di: Feng, Xiao, et al.
Pubblicazione: (2026)

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

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

CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
di: Lin, Shen, et al.
Pubblicazione: (2026)

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
di: Wu, Yuhao, et al.
Pubblicazione: (2024)

On Large Language Model Continual Unlearning
di: Gao, Chongyang, et al.
Pubblicazione: (2024)

SUA: Stealthy Multimodal Large Language Model Unlearning Attack
di: Zhang, Xianren, et al.
Pubblicazione: (2025)

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

A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
di: Feng, Xiaohua, et al.
Pubblicazione: (2025)

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
di: Mozafari, Mostafa, et al.
Pubblicazione: (2025)

Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
di: Li, Xuan, et al.
Pubblicazione: (2023)

Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
di: Zhang, Yunbei, et al.
Pubblicazione: (2026)

Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
di: Li, Zexi, et al.
Pubblicazione: (2025)

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
di: Yang, Puning, et al.
Pubblicazione: (2026)

Leveraging Per-Instance Privacy for Machine Unlearning
di: Sepahvand, Nazanin Mohammadi, et al.
Pubblicazione: (2025)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
di: Gambardella, Andrew, et al.
Pubblicazione: (2024)

Mitigating Label Noise on Graph via Topological Sample Selection
di: Wu, Yuhao, et al.
Pubblicazione: (2024)

Large Language Diffusion Models
di: Nie, Shen, et al.
Pubblicazione: (2025)

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
di: Zeng, Siqi, et al.
Pubblicazione: (2025)

LLM Unlearning with LLM Beliefs
di: Li, Kemou, et al.
Pubblicazione: (2025)

Long-tailed Recognition with Model Rebalancing
di: Luo, Jiaan, et al.
Pubblicazione: (2025)

Amortized Reasoning Tree Search: Decoupling Proposal and Decision in Large Language Models
di: Hong, Zesheng, et al.
Pubblicazione: (2026)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
di: Yuan, Hongbang, et al.
Pubblicazione: (2024)