jailbreakbench:基于大语言模型的鲁棒性基准测试项目

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

分支11Tags4

项目介绍

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

定制我的领域