Cover Image

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dorna, Vineeth, Mekala, Anmol, Zhao, Wenlong, McCallum, Andrew, Lipton, Zachary C., Kolter, J. Zico, Maini, Pratyush
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TOFU: A Task of Fictitious Unlearning for LLMs
by: Maini, Pratyush, et al.
Published: (2024)

Rethinking LLM Memorization through the Lens of Adversarial Compression
by: Schwarzschild, Avi, et al.
Published: (2024)

Understanding Hallucinations in Diffusion Models through Mode Interpolation
by: Aithal, Sumukh K, et al.
Published: (2024)

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
by: Maini, Pratyush, et al.
Published: (2023)

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
by: Goyal, Sachin, et al.
Published: (2024)

Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
by: Mekala, Anmol, et al.
Published: (2024)

When Should We Introduce Safety Interventions During Pretraining?
by: Sam, Dylan, et al.
Published: (2026)

AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs
by: Akinwande, Victor, et al.
Published: (2024)

Existing Large Language Model Unlearning Evaluations Are Inconclusive
by: Feng, Zhili, et al.
Published: (2025)

Safety Pretraining: Toward the Next Generation of Safe AI
by: Maini, Pratyush, et al.
Published: (2025)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
by: Bansal, Hritik, et al.
Published: (2025)

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

Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks
by: Kim, Eungyeup, et al.
Published: (2026)

A proof of P!=NP
by: McCallum, Rupert
Published: (2020)

Maximize Resource Recovery Synergies for Infrastructure Projects
by: Conrad McCallum
Published: (2024)

Inconsistency of Reinhardt cardinals with $\mathsf{ZF}$
by: McCallum, Rupert
Published: (2026)

Extending MARC for Bibliographic Control in the Web Environment: Challenges and Alternatives.
by: McCallum, Sally
Published: (2000)

The On-Line ERIC Project at the National Library of Australia.
by: McCallum, Ian S.
Published: (1976)

Information Technology Standards: Implementation, Maintenance, and Coordination.
by: McCallum, Sally
Published: (1993)

Returning to Ithaca To Get On with the Mission: Defining Value in Terms of Our Contribution to our Customers and Our Profession.
by: McCallum, Ian
Published: (2002)

From Malin Head to Mizen Head: A Journey Around the Sea Area Forecast, JoannaDonnelly, Gill Books, 2023, Hardback £21‐99, 244 pp., ISBN 978‐0‐71‐719736‐1
by: Ewen McCallum
Published: (2024)

Users' and providers' perspectives on technological procedures for 'normal' childbirth in a public maternity hospital in Salvador, Brazil
by: Cecilia McCallum
Published: (2008)

O dilema de uma prática: experiências de aborto em uma maternidade pública de Salvador, Bahia
by: Cecilia McCallum
Published: (2016)

Parentesco, gênero e individuação no cotidiano da casa em um bairro popular de Salvador da Bahia
by: Cecilia McCallum
Published: (2012)

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching
by: Angell, Rico, et al.
Published: (2023)

Auditing Language Model Unlearning via Information Decomposition
by: Goel, Anmol, et al.
Published: (2026)

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
by: Fan, Chongyu, et al.
Published: (2025)

Rethinking Distance Metrics for Counterfactual Explainability
by: Williams, Joshua Nathaniel, et al.
Published: (2024)

Benchmarking Unlearning for Vision Transformers
by: Zhao, Kairan, et al.
Published: (2026)

Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval
by: Song, Jonghyun, et al.
Published: (2024)

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

Unlearning in LLMs: Methods, Evaluation, and Open Challenges
by: Lizzo, Tyler, et al.
Published: (2026)

Unlearning during Learning: An Efficient Federated Machine Unlearning Method
by: Gu, Hanlin, et al.
Published: (2024)

Mimetic Initialization of MLPs
by: Trockman, Asher, et al.
Published: (2026)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
by: Cadet, Xavier F., et al.
Published: (2024)

OpenGU: A Comprehensive Benchmark for Graph Unlearning
by: Fan, Bowen, et al.
Published: (2025)

Comprehensive VLBI observations of Galileo satellites with the AuScope array
by: Schunck, David, et al.
Published: (2026)

An experiment to observe GNSS signals with the Australian VGOS array
by: McCallum, Lucia, et al.
Published: (2024)

Export processing zones: comparative data from China, Honduras, Nicaragua, and South Africa
by: Jamie K. McCallum
Published: (2011)

Le problème des "régions éprouvées" en Grande-Bretagne
by: E. D. McCallum
Published: (1934)