实体 safety benchmarks

safety benchmarks

PulseAugur coverage of safety benchmarks — every cluster mentioning safety benchmarks across labs, papers, and developer communities, ranked by signal.

Show in brief

总计 · 30天

90 天内 1

发布 · 30天

90 天内 0

论文 · 30天

90 天内 1

层级分布 · 90 天

最近 · 第 1/1 页 · 共 1 条

RESEARCH · CL_09837 · Apr 28 · 23:21

Researchers develop test-time safety alignment for LLMs using input embeddings

Researchers have developed a novel method for enhancing the safety of aligned AI models by manipulating input word embeddings. This technique uses gradient descent on embeddings, guided by a black-box text moderation AP…

Researchers develop test-time safety alignment for LLMs using input embeddings