站内快照 · 国内可打开。外网原文可能无法访问。
- 论文公开站arXiv
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. TasteVal measures the experimental component o