Guardrail Baselines for Unlearning in LLMs

arXiv:2403.03329v1 Announce Type: new
Abstract: Recent work has demonstrated that fine-tuning is a promising approach to `unlearn' concepts from large language models. However, fine-tuning can be expensive, as it requires both generating a set of examples and running iterations of fine-tuning to update the model. In this work, we show that simple guardrail-based approaches such as prompting and filtering can achieve unlearning results comparable to fine-tuning. We recommend that researchers investigate these lightweight baselines when evaluating the performance of more …

abstract arxiv concepts cs.cl examples fine-tuning guardrail however language language models large language large language models llms running set show simple type unlearning update work