SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.20516 · 2024

Machine Unlearning in Generative AI: A Survey

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. However, the models would memorize and generate sensitive, biased, or dangerous information originated from the training data especially those from web crawl. New machine unlearning (MU) techniques are being developed to reduce or eliminate undesirable knowledge and its effects from the models, because those that were designed for traditional classification tasks could not be applied for Generative AI. We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques. It also presents several critical challenges and promising directions in MU research. A curated list of readings can be found: https://github.com/franciscoliu/GenAI-MU-Reading.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.20516")
get_code_for_paper("2407.20516")
have("2407.20516")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.20516.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.20516.svg)](https://syntology.ai/paper/2407.20516)

Connect an agent — have() is free.