发表机构
New York University Abu Dhabi; Multimedia University; University of Florida（纽约大学阿布扎比分校; 多媒体大学; 佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究构建LLM模拟学术守门场景，发现LLM存在学术地位偏差，且模型架构导致区域偏好差异，凸显需审计AI系统的公平性与价值对齐。
AI 中文摘要
科学知识的公平获取往往依赖于非正式的守门决策，尤其是在必须选择性共享付费墙文章、数据集或简历（CV）等专业材料这类资源时。我们引入了一个受控模拟框架，其中基于大语言模型（LLM）的教授必须仅向一名请求者授予权限。在不同提示下，请求者在全球区域（全球北方 vs. 全球南方）和学术资历（本科生、博士候选人、博士后研究员、终身教授）方面存在系统性差异，而所有其他因素保持不变。在不同评估场景中，LLM表现出截然不同的学术地位偏差，部分模型优先考虑博士候选人，而另一些则倾向于终身教授。然而，当全球区域不同时，会出现基于模型架构的明显分歧：尽管许多前沿LLM由于以公平为导向的安全对齐而表现出亲公平偏差，系统性地偏向全球南方的请求者，但开源权重模型和小型模型经常将这种偏好反转，转而偏向全球北方，这反映了其基线预训练数据的全球区域偏差和未对齐的地理分布。我们的研究结果强调，模型行为中嵌入的规范假设如何影响守门决策，凸显了对AI系统进行公平性和价值对齐审计的重要性。
英文摘要
Equitable access to scientific knowledge often depends on informal gatekeeping decisions, particularly when resources such as paywalled articles, datasets, or professional materials such as curriculum vitae (CV) must be shared selectively. We introduce a controlled simulation framework in which large language model (LLM)-based professors must grant access to only one requestor. Across prompts, requesters vary systematically by global region (Global North vs. Global South) and academic seniority (undergraduate student, PhD candidate, postdoctoral researcher, and tenured professor), while all other factors remain constant. Across varying evaluation scenarios, LLMs exhibit contrasting academic status biases, with some prioritizing PhD candidates, while others favor tenured professors. However, when global regions differ, a distinct divergence emerges based on model architecture: while many frontier LLMs systematically favor requesters from the Global South due to pro-equity bias that results from equity-focused safety alignment, open-weight and small models frequently flip this preference to favor the Global North, reflecting the global region bias and unaligned geographic distribution of their baseline pre-training data. Our findings highlight how normative assumptions embedded in model behavior can shape gatekeeping decisions, underscoring the importance of auditing AI systems for fairness and value alignment.
