SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
For AI safety researchers, this benchmark provides a structured way to assess and compare LLM safety in scientific contexts, addressing the underspecified risk dimensions in prior work.
The paper introduces SciRisk-Bench, a benchmark for evaluating AI4Science safety across 7 disciplines, 31 subdisciplines, and 10 risk dimensions. Experiments show that both mainstream and science-oriented LLMs exhibit safety gaps, enabling fine-grained diagnosis of unsafe behaviors.
Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery. This progress creates an urgent need for safety benchmarks that evaluate not only scientific competence, but also whether models recognize and avoid risks in high-stakes scientific contexts. Existing AI4Science safety datasets cover several disciplines and task formats, leaving the underlying risk dimensions underspecified. We introduce \textbf{SciRisk-Bench}, a benchmark designed to evaluate AI4Science safety from two complementary perspectives: explicit risk dimensions and scientific disciplines. SciRisk-Bench covers 7 disciplines, 31 subdisciplines and 10 risk dimensions. In the experimental section, we evaluate both mainstream LLMs and science-oriented LLMs across risk dimensions, disciplines, and sub-disciplines, enabling fine-grained diagnosis of where scientific models remain unsafe.