1
Investigating and Alleviating Harm Amplification in LLM Interactions
LLM也会「助纣为虐」？这篇论文揭露了对话式AI如何被恶意利用放大伤害，并给出缓解方案
arXiv:2606.02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm …