研究人员正在开发用于高效大型语言模型（LLM）对齐和微调的新方法。一种名为P2D的方法使用任务敏感的注意力头来指导数据选择和参数剪枝，从而实现显著的速度提升和性能提升。另一个研究领域专注于联邦微调，即模型在不共享原始数据的情况下跨多个客户端进行协作训练。ShaPO等新框架通过控制优化几何来解决安全对齐中的鲁棒性问题，而其他研究则探索基于行为的共识和面向联邦LoRA微调的污染感知技术。 AI
影响 这些论文介绍了更高效、更鲁棒的LLM训练和对齐的新技术，有望降低计算成本并提高模型安全性。
排序理由 该集群包含多篇学术论文，详细介绍了LLM对齐和联邦微调的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →
arXiv:2605.24154v1 Announce Type: new Abstract: Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users…
arXiv:2605.21602v2 Announce Type: replace Abstract: Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether L…
arXiv:2602.07340v2 Announce Type: replace Abstract: Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced…
arXiv:2605.21558v1 Announce Type: cross Abstract: Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selection and parameter-efficient fine-tuning as isolated…
Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM monitoring pipelines can detect these OOD alignme…
Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem. However, even parameter-efficient methods require transmitting large collections of trainable weights, assume aligned architectures, and rely on white-box access to model par…
arXiv:2605.21217v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA under a federated learning setting, enabling collaborative fine-tuning across cli…
Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA under a federated learning setting, enabling collaborative fine-tuning across clients while preserving parameter efficiency. We f…