Image de couverture de livre

UniErase: Towards Balanced and Precise Unlearning in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Miao, Lin, Liang, Zhang, Guibin, Li, Xinfeng, Fang, Junfeng, Yu, Xingrui, Tsang, Ivor, Zhang, Ningyu, Wang, Kun, Wang, Yang
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models
par: Wu, Jingxuan, et autres
Publié: (2026)

Multi-agent Architecture Search via Agentic Supernet
par: Zhang, Guibin, et autres
Publié: (2025)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
par: Tian, Bozhong, et autres
Publié: (2024)

Advancing Analytic Class-Incremental Learning through Vision-Language Calibration
par: Zhao, Binyu, et autres
Publié: (2026)

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
par: Li, Zherui, et autres
Publié: (2025)

HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding
par: Xing, Bowen, et autres
Publié: (2024)

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
par: Zhang, Guibin, et autres
Publié: (2025)

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
par: Lin, Liang, et autres
Publié: (2025)

Explainable LLM Unlearning Through Reasoning
par: Liao, Junfeng, et autres
Publié: (2026)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
par: Yu, Miao, et autres
Publié: (2024)

AnyEdit: Edit Any Knowledge Encoded in Language Models
par: Jiang, Houcheng, et autres
Publié: (2025)

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
par: Chen, Cheng, et autres
Publié: (2025)

Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models
par: Sun, Zhengke, et autres
Publié: (2025)

Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models
par: Wang, Yujing, et autres
Publié: (2025)

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
par: Sun, Ming, et autres
Publié: (2026)

Neuron-Level Sequential Editing for Large Language Models
par: Jiang, Houcheng, et autres
Publié: (2024)

Reflection-Driven Control for Trustworthy Code Agents
par: Wang, Bin, et autres
Publié: (2025)

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
par: Wu, Jiawei, et autres
Publié: (2026)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
par: Deng, Chenlong, et autres
Publié: (2025)

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
par: Li, Hongji, et autres
Publié: (2025)

ReLearn: Unlearning via Learning for Large Language Models
par: Xu, Haoming, et autres
Publié: (2025)

BlindU: Blind Machine Unlearning without Revealing Erasing Data
par: Wang, Weiqi, et autres
Publié: (2026)

Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
par: Wang, Huazheng, et autres
Publié: (2025)

Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia
par: Yu, Miao, et autres
Publié: (2024)

Collaborative Knowledge Infusion for Low-resource Stance Detection
par: Yan, Ming, et autres
Publié: (2024)

Neighboring Perturbations of Knowledge Editing on Large Language Models
par: Ma, Jun-Yu, et autres
Publié: (2024)

On the Role of Attention Heads in Large Language Model Safety
par: Zhou, Zhenhong, et autres
Publié: (2024)

PairUni: Pairwise Training for Unified Multimodal Language Models
par: Zheng, Jiani, et autres
Publié: (2025)

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
par: Yan, Xin, et autres
Publié: (2026)

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
par: Lin, Liang, et autres
Publié: (2025)

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
par: Zhang, Guibin, et autres
Publié: (2025)

From Data to Behavior: Predicting Unintended Model Behaviors Before Training
par: Wang, Mengru, et autres
Publié: (2026)

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks
par: Zhou, Yu, et autres
Publié: (2025)

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
par: Zhang, Xiang, et autres
Publié: (2025)

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
par: Wan, Zhenglin, et autres
Publié: (2025)

Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
par: Wu, Jingxuan, et autres
Publié: (2025)

Erasing Conceptual Knowledge from Language Models
par: Gandikota, Rohit, et autres
Publié: (2024)

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
par: Zhuo, Xingrui, et autres
Publié: (2025)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
par: Jiang, Houcheng, et autres
Publié: (2026)

Mem-W: Latent Memory-Native GUI Agents
par: Zhang, Guibin, et autres
Publié: (2026)