Institutional Prestige as Geographic Bias in Large Language Models: Evidence from Three Factorial Experiments with Bootstrap Confidence Intervals
大型语言模型中作为地理偏见的机构声望:来自三项带自助法置信区间的析因实验的证据
机构 * Universidad Bolivariana del Ecuador(厄瓜多尔玻利瓦尔大学) ; Universidad de Guayaquil(瓜亚基尔大学) ; University of New Mexico(新墨西哥大学)
专题命中 评测与基准 :large language model(title,abstract);language model(title,abstract);LLM(abstract);分类 cs.CL、cs.AI
AI总结 该研究通过三项带自助法置信区间的析因实验,发现大型语言模型在候选人评估中存在机构声望、期刊声望及国籍相关的偏见,期刊声望影响远大于机构声望,还证实了发表于《自然》的救助效应。
Comments 11 pages, 3 figures. Extended English version of an earlier two-study Spanish-language paper published in Neutrosophic Computing and Machine Learning (2026); this version adds Study 3 (journal x institution prestige) and bootstrap confidence intervals throughout