arXiv：cs.AI· Yifan He, Manon Reusens, Sofie Goethals, David Martens·· 5 小时前
研究：LLM 如何在全球范围内为人类时间定价
A Global View of How LLMs Value Human Time
AI 导读
一项研究通过让 LLM 为 60 分钟预约延迟给出补偿金额，考察其对不同国家用户时间价值的判断。结果覆盖 193 个国家和 5 个 LLM，模型一致对欧洲用户给出最高补偿，对非洲用户多为最低，并按 GDP_PPP 低估了亚洲和南美用户的时间价值。研究表明地理偏好已嵌入 LLM，可能在智能体场景中带来差异化对待。
正文
Abstract:Large language models (LLMs) increasingly act as personal assistants; however, little is known about how they capture national-level preferences on a global scale. Given that "time" is a universal and representative concept, we examine LLMs' time preferences by varying only users' country and measuring the compensation LLMs deem appropriate for a 60-minute appointment delay. We then compare LLMs' responses with GDP per capita on Purchasing Power Parity (GDP_PPP), Mean Income, and a literature-based index (Patience Score). Our results across 193 countries and 5 LLMs demonstrate that people's time across the world is evaluated in noticeably different ways among LLMs, as well as varying levels of robustness under prompt variations. LLMs consistently recommend the highest compensation for Europe, but mostly the lowest for Africa. Based on GDP_PPP, LLMs underestimate the value of time for users living in Asia and South America. These findings indicate that geographical patterns are embedded in LLMs and may translate in different treatment in agentic settings.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18515 [cs.CY] |
| (or arXiv:2610.18515v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18515 arXiv-issued DOI via DataCite |
Submission history
From: Yifan He [view email]
[v1]
Tue, 13 Oct 2026 15:08:38 UTC (5,300 KB)
[v2]
Wed, 14 Oct 2026 08:41:00 UTC (5,300 KB)
来源：arXiv：cs.AI · arxiv.org