English(EN) Evaluating Geographic Lexical Knowledge in Large Language Models Across 21 Spanish-Speaking Countries

大型语言模型在西班牙语地理词汇知识方面表现不均

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

一项新研究评估了十个大型语言模型（LLMs）在21个西班牙语国家的地理词汇知识。研究使用了专家策划的数据和两种问题格式（是/否和多项选择）来评估LLMs对西班牙语地区差异的理解程度。结果表明，根据模型、国家和问题格式的不同，性能存在显著差异，其中西班牙得分最高，智利得分最低。 AI

影响强调了LLMs需要更好地理解地区语言差异，以实现全球可用性。

排序理由评估LLM能力的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 评估LLM能力的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Yoshifumi Kawasaki · 2026-10-28 04:00

评估21个西班牙语国家大型语言模型的地理词汇知识

arXiv:2602.09346v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly serve users across regional varieties, yet their knowledge of geographic lexical variation remains insufficiently evaluated. We investigate country-conditioned lexical usage judgments in…