2 results found Sort:

IS2Lab
S-Eval IS2Lab
3
56
other
4
S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models
benchmark test-generation safety-evaluation large-language-models
Created 2024-05-13
56 commits to main branch, last one about a month ago
SORRY-Bench
sorry-bench SORRY-Bench
2
50
mit
1
Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)
llm refusal benchmark safety-evaluation
Created 2024-06-13
6 commits to main branch, last one 27 days ago