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

arXiv:2405.03097v1 Announce Type: new
Abstract: 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 deal with these side-effects of memorized data, while not hurting the model's utility. We offer a fresh perspective towards this goal, namely, that each textual sequence to be …

abstract arxiv copyright cs.ai cs.cl cs.lg data form found improving language language models large language large language models llms privacy said text text generation textual training type unlearning