arXiv cs.CL· Kento Haneda, Yosuke Kishinami, Ryo Fujii, Keisuke Sakaguchi, Makoto Morishita·· 13 小时前AI 评分31
WikiOriginQA：自动构建带知识来源的问答数据集，用于分析文化偏见
WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias
AI 导读
研究者提出 WikiOriginQA，通过不同 Wikipedia 语言版本的创建日期客观标注知识来源，自动构建带知识来源的问答数据集，无需人工标注。实验显示 LLM 表现倾向偏向英语圈文化，并表明知识向英语圈传播的重要性。该数据集已被 AACL-IJCNLP 2026 接收，可在多语言下以更高可扩展性开展文化偏见评估。
正文 · 原文
Abstract:Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture. However, the process requires considerable human effort, presenting a significant challenge to scalability. To address this challenge, we introduce WikiOriginQA, a QA dataset automatically constructed by objectively representing the origins of knowledge through the creation dates of different Wikipedia language editions. Experimental results with the created dataset confirm that LLM performance tends to be biased toward Anglophone cultures. Furthermore, the results suggest the importance of knowledge propagation into the Anglosphere. These findings demonstrate the validity of our automated approach, enabling cultural bias evaluations with superior scalability across diverse languages without extensive manual annotation.
| Comments: | Accepted to AACL-IJCNLP 2026 (9 pages, 2 figures, 10 tables) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.30677 [cs.CL] |
| (or arXiv:2610.30677v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30677 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kento Haneda [view email]
[v1]
Thu, 22 Oct 2026 03:42:37 UTC (559 KB)
来源：arXiv cs.CL · arxiv.org