Patent for Unlearning Text Data in LLMs

← USPTO Patent Applications

UNLEARNING TEXT DATA FROM TRAINED LARGE LANGUAGE MODELS

Application US20260099705A1 Kind: A1 Apr 09, 2026

Assignee

Hirundo LTD

Inventors

Tomer RAVIV, Oded SHMUELI

Abstract

There is provided a computer implemented method of unlearning text data from a trained large language model (LLM), comprising: accessing a trained LLM trained on a training dataset of text data, selecting a first set of text data for being retained and a second set of text data for being unlearned, computing a domain separation for the trained LLM to disentangle the representations of the first set of text data and the second text within a latent representation space of the trained LLM by adapting weights of a set of neurons of the trained LLM, and generating an adapted LLM from the trained LLM, the adapted LLM comprising the trained LLM with the adapted weights in response to the domain separation.

CPC Classifications

G06N 3/08

Filing Date

2025-07-24

Application No.

19278971

View original document →