Imagen de Portada

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Weijia, Lee, Jaechan, Huang, Yangsibo, Malladi, Sadhika, Zhao, Jieyu, Holtzman, Ari, Liu, Daogao, Zettlemoyer, Luke, Smith, Noah A., Zhang, Chiyuan
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Evaluating Copyright Takedown Methods for Language Models
por: Wei, Boyi, et al.
Publicado: (2024)

Detecting Pretraining Data from Large Language Models
por: Shi, Weijia, et al.
Publicado: (2023)

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
por: Huang, Yangsibo, et al.
Publicado: (2024)

Fantastic Copyrighted Beasts and How (Not) to Generate Them
por: He, Luxi, et al.
Publicado: (2024)

Scaling Embedding Layers in Language Models
por: Yu, Da, et al.
Publicado: (2025)

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
por: Chua, Lynn, et al.
Publicado: (2024)

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
por: Min, Sewon, et al.
Publicado: (2023)

Trainable Transformer in Transformer
por: Panigrahi, Abhishek, et al.
Publicado: (2023)

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
por: Malladi, Sadhika, et al.
Publicado: (2022)

Provable unlearning in topic modeling and downstream tasks
por: Wei, Stanley, et al.
Publicado: (2024)

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
por: Hu, Yushi, et al.
Publicado: (2024)

An Adversarial Perspective on Machine Unlearning for AI Safety
por: Łucki, Jakub, et al.
Publicado: (2024)

Quantifying Cross-Modality Memorization in Vision-Language Models
por: Wen, Yuxin, et al.
Publicado: (2025)

Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling
por: Li, Margaret, et al.
Publicado: (2024)

Linearly Decoding Refused Knowledge in Aligned Language Models
por: Shrivastava, Aryan, et al.
Publicado: (2025)

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing
por: Holtzman, Ari, et al.
Publicado: (2026)

Metadata Conditioning Accelerates Language Model Pre-training
por: Gao, Tianyu, et al.
Publicado: (2025)

Demystifying Prompts in Language Models via Perplexity Estimation
por: Gonen, Hila, et al.
Publicado: (2022)

In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
por: Panigrahi, Abhishek, et al.
Publicado: (2025)

Progressive distillation induces an implicit curriculum
por: Panigrahi, Abhishek, et al.
Publicado: (2024)

LESS: Selecting Influential Data for Targeted Instruction Tuning
por: Xia, Mengzhou, et al.
Publicado: (2024)

The Marginal Value of Momentum for Small Learning Rate SGD
por: Wang, Runzhe, et al.
Publicado: (2023)

Fine-Tuning Language Models with Just Forward Passes
por: Malladi, Sadhika, et al.
Publicado: (2023)

Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
por: Gonen, Hila, et al.
Publicado: (2024)

The Coverage Principle: How Pre-Training Enables Post-Training
por: Chen, Fan, et al.
Publicado: (2025)

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
por: Jiang, Yiding, et al.
Publicado: (2024)

Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
por: Yasunaga, Michihiro, et al.
Publicado: (2025)

AI as Entertainment
por: Kommers, Cody, et al.
Publicado: (2026)

Prompting as Scientific Inquiry
por: Holtzman, Ari, et al.
Publicado: (2025)

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
por: Razin, Noam, et al.
Publicado: (2024)

LMFusion: Adapting Pretrained Language Models for Multimodal Generation
por: Shi, Weijia, et al.
Publicado: (2024)

Overtrained Language Models Are Harder to Fine-Tune
por: Springer, Jacob Mitchell, et al.
Publicado: (2025)

In-context Pretraining: Language Modeling Beyond Document Boundaries
por: Shi, Weijia, et al.
Publicado: (2023)

Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models
por: Blevins, Terra, et al.
Publicado: (2024)

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
por: Chua, Lynn, et al.
Publicado: (2024)

On Memorization of Large Language Models in Logical Reasoning
por: Xie, Chulin, et al.
Publicado: (2024)

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
por: Shao, Rulin, et al.
Publicado: (2024)

ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
por: Chen, Tong, et al.
Publicado: (2025)

Anode‐Free All‐Solid‐State Batteries: Understanding Limitations and Charting a Path to Enhanced Performance
por: Sion Kim, et al.
Publicado: (2026)

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon
por: Yang, Chenghao, et al.
Publicado: (2025)