paper-with-me

홈 › Papers

Classifier-free guidance in LLMs Safety

2024-12-08 · Roman Smirnov

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.

📄 PDF Abstract BibTeX arXiv:2412.06846

Code (1)

rgsmirnov/cfg_safety_llm 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

SafeCFG: Redirecting Harmful Classifier-Free Guidance for Safe Generation

2024-12-20 · Jiadong Pan, Hongcheng Gao, Liang Li, Zheng-Jun Zha 외

Diffusion models (DMs) have demonstrated exceptional performance in text-to-image (T2I) tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), the quality of images generated by …

Image Generation

Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance

2024-02-13 · Linxi Zhao, Yihe Deng, Weitong Zhang, Quanquan Gu

The advancement of Large Vision-Language Models (LVLMs) has increasingly highlighted the critical issue of their tendency to hallucinate non-existing objects in the images. To address this issue, previous works focused o…

HallucinationObject Hallucination

Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective

2025-03-13 · Xiaoming Zhao, Alexander G. Schwing

Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an …

Denoising

Classifier-Free Diffusion Guidance

2022-07-26 · Jonathan Ho, Tim Salimans

Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other type…

Diversity

C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis

2026-03-09 · Jiayang Gao, Tianyi Zheng, Jiayang Zou, Fengxiang Yang 외 arxiv

Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirical and overlooks the inherent dynamics of…