论文提出用长尾性能评估LLM创造力并引入q@Tail指标

1. 12:00
   arXiv · Computation and Language

   通过长尾表现评估 LLM 创造力

   研究提出用参考输入-输出分布长尾中的任务特定表现来形式化 LLM 创造力，基于新颖性-质量乘积框架，在 15 个基准和 26 个开放权重模型上以预训练数据 n-gram 缺失作为新颖性代理进行实证。

Current heat 9·Comparable peak 10（Oct 12）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.