Classifier-free guidance in LLMs Safety
On the map: LLM safety and security → Machine unlearning
Abstract (arXiv)
The paper describes LLM unlearning without a retaining dataset, using the ORPO reinforcement learning method with inference enhanced by modified classifier-free guidance. Significant improvement in unlearning, without degradation of the model, is achieved through direct training on synthetic replacement data in CFG-aware training regime, with classifier-free guidance applied during the inference. This article is an extended version of the NeurIPS 2024 LLM-PC submission, which was awarded second prize.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 8 of its 9 references that are in the map. First posted on arXiv 8 Dec 2024.
Builds on
8 of 9 references.
Closest ancestors · 4
Same direction, newest first
- 2023Large Language Model Unlearning14 Oct
- 2023In-Context Unlearning: Language Models as Few Shot Unlearners11 Oct
- 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
- 2023KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment11 May
Other references · 4
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
- 2022Editing Models with Task Arithmeticcited by 1,076
- 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 556
- 2023Stay on topic with Classifier-Free Guidancecited by 90
Built on by
Citing papers per year: 2025: 1.
1 paper.