1
NeST: Neuron Selective Tuning for LLM Safety
大模型安全新方案：通过神经元选择性调优NeST精准提升LLM安全性，不牺牲性能。
arXiv:2602.16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs)…
2
Detecting Functional Memorization in Code Language Models
新研究提出检测代码大模型“功能性记忆”的方法，直击模型抄袭与数据泄露隐患。
arXiv:2606.12764v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work …