arXiv · Computation and Language· Mengze Hong, Zeyang Lei, Wenbo Shang, Xia Zeng, Xiying Zhao, Qi Zhu, Chen Jason Zhang, Di Jiang, Taiming Fu, Qiongyi Zhou, Qinghe Chang, Fubao Zhang, Chenxuan Ma, Minlong Peng, Jinfeng Huang, Zineng Zhou, Jindou Wu, Muge Qi, Sijun He, Xin Cui, Di Liang, Yuan Hua, Davey Chen·· 3 小时前AI 评分33
UXBench Pro：面向多轮对话交互的个性化用户体验基准
UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions
AI 导读
研究者提出 UXBench 基准，包含 1,000 个来自 12 个任务场景和 82 个领域的测试实例，每个实例配有刻画七类可解释行为维度的 FACTORS 用户画像。
来源：arXiv · Computation and Language · arxiv.org