对比跨文化好奇心表达，发现大模型倾向西方模式并可优化
The Curious Case of Curiosity across Human Cultures and LLMs
- 用真实多国问答数据构建文化好奇度评估框架
- 模型普遍弱化文化差异，与西方表达更接近
- 微调可提升50%跨文化对齐度，增强模型适应性
大语言模型在人机交互中日益重要，但其好奇心表现——尤其是跨文化差异——仍缺乏研究。本文基于涵盖多元主题的跨国真实数据集Yahoo! Answers，提出CUEST（CUriosity Evaluation across SocieTies）评估框架，通过语言风格、话题偏好分析及社会学理论支撑，衡量人类与模型在好奇心表达上的对齐程度。实验发现，无论开源或闭源模型均弱化跨文化多样性，更贴近西方国家的好奇表达方式。通过微调策略可使模型与人类在好奇心表达上的差距缩小最高达50%。结果表明，好奇心对提升大模型跨文化适应能力具有实际价值，为未来NLP研究提供新方向。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) have expanded their role in human interaction, yet curiosity -- a central driver of inquiry -- remains underexplored in these systems, particularly across cultural contexts. In this work, we investigate cultural variation in curiosity using Yahoo! Answers, a real-world multi-country dataset spanning diverse topics. We introduce CUEST (CUriosity Evaluation across SocieTies), an evaluation framework that measures human-model alignment in curiosity through linguistic (style), topic preference (content) analysis and grounding insights in social science constructs. Across open- and closed-source models, we find that LLMs flatten cross-cultural diversity, aligning more closely with how curiosity is expressed in Western countries. We then explore fine-tuning strategies to induce curiosity in LLMs, narrowing the human-model alignment gap by up to 50%. Finally, we demonstrate the practical value of curiosity for LLM adaptability across cultures, showing its importance for future NLP research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。