1
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
用隐藏状态探针在流式生成中提前审核LLM输出，中断不当内容并节省算力
arXiv:2606.10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering. E…