Data Leverage References

← Back to browse

Tag: unlearning (7 references)

Rethinking machine unlearning for large language models 2025 article

Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Yuguang Yao, Chris Yuhao Liu, Xiaojun Xu, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, Yang Liu

Comprehensive review of machine unlearning in LLMs, aiming to eliminate undesirable data influence (sensitive or illegal information) while maintaining essential knowledge generation. Envisions LLM unlearning as a pivotal element in life-cycle management for developing safe, secure, trustworthy, and resource-efficient generative AI.

LLM Unlearning via Loss Adjustment with Only Forget Data 2024 inproceedings

Yaxuan Wang, Jiaheng Wei, Chris Yuhao Liu, Jinlong Pang, Quan Liu, Ankit Parag Shah, Yujia Bao, Yang Liu, Wei Wei

FLAT is a loss adjustment approach which maximizes f-divergence between the available template answer and the forget answer with respect to the forget data. Demonstrates superior unlearning performance compared to existing methods while minimizing impact on retained capabilities, tested on Harry Potter dataset and MUSE Benchmark.

Machine Unlearning: A Survey 2024 article

Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, Philip S. Yu

Comprehensive survey of machine unlearning covering definitions, scenarios, verification methods, and applications. Cited in the International AI Safety Report 2025 as a pioneering paradigm for removing sensitive information.

LEACE: Perfect linear concept erasure in closed form 2023 article

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman

Datamodels: Predicting Predictions from Training Data 2022 inproceedings

Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, Aleksander Madry

Proposes datamodels that predict model outputs as a function of training data subsets, providing a framework for understanding data attribution through retraining experiments.

Machine Unlearning 2021 inproceedings

Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot

Introduces SISA (Sharded, Isolated, Sliced, Aggregated) training for efficient exact machine unlearning. Partitions data into shards with separate models, enabling targeted retraining when data must be forgotten.

Towards Making Systems Forget with Machine Unlearning 2015 inproceedings

Yinzhi Cao, Junfeng Yang

First formal definition of machine unlearning. Proposes converting learning algorithms into summation form to enable efficient data removal without full retraining. Foundational work establishing the unlearning problem.