HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal Paper • 2402.04249 • Published Feb 6, 2024 • 8
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation Paper • 2506.14028 • Published Jun 16, 2025 • 94