Pith. sign in

Machine unlearning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2024 1 2023 1

verdicts

CONDITIONAL 2

representative citing papers

Detecting Pretraining Data from Large Language Models

cs.CL · 2023-10-25 · conditional · novelty 7.0

Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.

TOFU: A Task of Fictitious Unlearning for LLMs

cs.LG · 2024-01-11 · conditional · novelty 6.0

TOFU is a new benchmark with synthetic profiles and metrics demonstrating that existing unlearning algorithms for LLMs fail to achieve effective forgetting of targeted information.

citing papers explorer

Showing 2 of 2 citing papers.

  • Detecting Pretraining Data from Large Language Models cs.CL · 2023-10-25 · conditional · none · ref 4

    Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.

  • TOFU: A Task of Fictitious Unlearning for LLMs cs.LG · 2024-01-11 · conditional · none · ref 1

    TOFU is a new benchmark with synthetic profiles and metrics demonstrating that existing unlearning algorithms for LLMs fail to achieve effective forgetting of targeted information.