← Search

George-Octavian Bărbulescu

2 accepted papers

2024

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models

ICML 2024poster

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then takes the form of devising new algorithms that will properly…

Cited by 19SourcePDFScholar
2024

What makes unlearning hard and what to do about it

NeurIPS 2024poster

Machine unlearning is the problem of removing the effect of a subset of training data (the ``forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove mislabeled, poisoned or otherwise problematic data. With unlearning…