When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation 文章

ArXiv CS.CL2026-05-27NEWSen作者: Wenda Xu, Sweta Agrawal, Vil\'em Zouhar, Markus Freitag, Daniel Deutsch
AI 芯片
查看原文 →
关系图谱

When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation · 相关人物

暂无数据