Language Models Agree With Each Other, Not With Readers
语言模型彼此意见一致,但与读者不一致
专题命中 其他LLM :language model(title,abstract);分类 cs.CL
AI总结 该研究以非研究专用的读者标记为参考,发现不同语言模型间的一致性高于模型与读者间的一致性,且模型一致性与模型规模等因素相关,样本外测试也验证了该结论。
Comments 18 pages. Ancillary files include all three pre-registrations, every analysis script and every result artifact; the paper contains no numeric literal for a measured value and make-numbers.py regenerates all of them from the shipped artifacts alone