K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

30秒で要点

何が起きたか

Researchers released K-Bench, a benchmark testing 125 LLM configurations across 33 base models on high-risk mental health conversations involving suicide, self-harm, and domestic violence.

なぜ重要か

Engineers building or deploying mental health chatbots need this to evaluate whether their models handle crisis situations safely and appropriately.

注意点

The benchmark uses synthetic conversations and a GPT-4o judge, not real clinical interactions, so real-world performance may differ from benchmark scores.