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.

Recent advances in generative AI have been driven by alignment techniques such as reinforcement learning from human feedback (RLHF). RLHF and related techniques typically involve constructing a dataset of binary or ranked choice human preferences and subsequently fine-tuning models to align with these preferences. This paper shifts the focus to understanding the preferences encoded in such datasets and identifying common human preferences. We find that a small subset of 21 preference categories (selected from a set of nearly 5,000 distinct preferences) captures >89% of preference variation across individuals. This small set of preferences is analogous to a canonical basis of human preferences, similar to established findings that characterize human variation in psychology or facial recognition studies. Through both synthetic and empirical evaluations, we confirm that our low-rank, canonical set of human preferences generalizes across the entire dataset and within specific topics. We further demonstrate our preference basis' utility in model evaluation, where our preference categories offer deeper insights into model alignment, and in model training, where we show that fine-tuning on preference-defined subsets successfully aligns the model accordingly.

What is the contribution that the arts and humanities can make to our engagement with the increasingly pervasive technology of artificial intelligence? My aim in this short article is to sketch some of these potential contributions. Perhaps the most fundamental contribution of the arts and humanities is to make vivid the fact that the development of AI is not a matter of destiny, but instead involves successive waves of highly consequential human choices. It's important to identify the choices, to frame them in the right way, and to raise the question: who gets to make them and how? This is important because AI, and digital technology generally, has become the latest focus of the historicist myth that social evolution is preordained, that our social world is determined by independent variables over which we, as individuals or societies, are able to exert little control.

What is the contribution that the arts and humanities can make to our engagement with the increasingly pervasive technology of artificial intelligence? My aim in this short article is to sketch some of these potential contributions. Perhaps the most fundamental contribution of the arts and humanities is to make vivid the fact that the development of AI is not a matter of destiny, but instead involves successive waves of highly consequential human choices. It's important to identify the choices, to frame them in the right way, and to raise the question: who gets to make them and how? This is important because AI, and digital technology generally, has become the latest focus of the historicist myth that social evolution is preordained, that our social world is determined by independent variables over which we, as individuals or societies, are able to exert little control. So we either go with the flow, or go under.