EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI Paper • 2509.11648 • Published Sep 15 • 1 • 2
D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning Paper • 2509.06771 • Published Sep 8 • 5 • 2
Deceptive Humor: A Synthetic Multilingual Benchmark Dataset for Bridging Fabricated Claims with Humorous Content Paper • 2503.16031 • Published Mar 20 • 3 • 2