1
STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
AI评估新范式：STABLEVAL在评估中引入分歧感知与稳定性，为AI系统的可靠评价提供创新方案。
arXiv:2605.02122v2 Announce Type: replace Abstract: Human evaluation remains the primary standard for assessing modern AI systems, yet annotator disag…