Image de couverture de livre

Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Iofinova, Eugenia, Alistarh, Dan
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SPADE: Sparsity-Guided Debugging for Deep Neural Networks
par: Moakhar, Arshia Soltani, et autres
Publié: (2023)

Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant
par: Nicolicioiu, Armand, et autres
Publié: (2024)

Position: It's Time to Act on the Risk of Efficient Personalized Text Generation
par: Iofinova, Eugenia, et autres
Publié: (2025)

Model Compression with Exact Budget Constraints via Riemannian Manifolds
par: Helcig, Michael, et autres
Publié: (2026)

Communication-Efficient Federated Learning With Data and Client Heterogeneity
par: Zakerinia, Hossein, et autres
Publié: (2022)

Fully Decentralized Certified Unlearning
par: Lamri, Hithem, et autres
Publié: (2025)

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models
par: Kurtic, Eldar, et autres
Publié: (2024)

LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs
par: Schultheis, Erik, et autres
Publié: (2025)

MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
par: Kleinegger, Maximilian, et autres
Publié: (2026)

Statistically-Lossless Quantization of Large Language Models
par: Helcig, Michael, et autres
Publié: (2026)

Powerset Convolutional Neural Networks
par: Wendler, Chris, et autres
Publié: (2019)

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
par: Ashkboos, Saleh, et autres
Publié: (2025)

Efficient Data Selection at Scale via Influence Distillation
par: Nikdan, Mahdi, et autres
Publié: (2025)

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
par: Panferov, Andrei, et autres
Publié: (2025)

Simple Opinion Dynamics for No-Regret Learning
par: Lazarsfeld, John, et autres
Publié: (2023)

Benchmarking Federated Machine Unlearning methods for Tabular Data
par: Xiao, Chenguang, et autres
Publié: (2025)

Apertus LLM Family Expansion via Distillation and Quantization
par: Panferov, Andrei, et autres
Publié: (2026)

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
par: Panferov, Andrei, et autres
Publié: (2026)

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
par: Sieberling, Oliver, et autres
Publié: (2024)

Towards Robust Scaling Laws for Optimizers
par: Volkova, Alexandra, et autres
Publié: (2026)

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
par: Hu, Shengyuan, et autres
Publié: (2024)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
par: Kadhe, Swanand Ravindra, et autres
Publié: (2024)

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
par: Dadgarnia, Alireza, et autres
Publié: (2026)

Towards Combinatorial Interpretability of Neural Computation
par: Adler, Micah, et autres
Publié: (2025)

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
par: Modoranu, Ionut-Vlad, et autres
Publié: (2026)

Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data
par: Shirgaonkar, Anup, et autres
Publié: (2024)

Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
par: Nakada, Ryumei, et autres
Publié: (2024)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
par: Cadet, Xavier F., et autres
Publié: (2024)

Beyond Outliers: A Study of Optimizers Under Quantization
par: Vlassis, Georgios, et autres
Publié: (2025)

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
par: Tabesh, Soroush, et autres
Publié: (2025)

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
par: Chen, Yiwei, et autres
Publié: (2025)

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
par: Ashkboos, Saleh, et autres
Publié: (2024)

How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
par: Qiu, Xinchi, et autres
Publié: (2024)

Quality Matters: Evaluating Synthetic Data for Tool-Using LLMs
par: Iskander, Shadi, et autres
Publié: (2024)

DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
par: Mahmud, Tamim Al, et autres
Publié: (2025)

Fast Exact Unlearning for In-Context Learning Data for LLMs
par: Muresanu, Andrei I., et autres
Publié: (2024)

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
par: Robert, Thomas, et autres
Publié: (2024)

Leverage Unlearning to Sanitize LLMs
par: Boutet, Antoine, et autres
Publié: (2025)

Efficacy of Synthetic Data as a Benchmark
par: Maheshwari, Gaurav, et autres
Publié: (2024)

Benchmarking the Fidelity and Utility of Synthetic Relational Data
par: Hudovernik, Valter, et autres
Publié: (2024)