Related papers: When Dialects Collide: How Socioeconomic Mixing Af…

Syntax connects words to each other in very specific ways. Two words are syntactically connected if they depend directly on each other. Syntactic connections usually happen within a sentence. Gathering all those connection across several…

Traditional approaches to urban income segregation focus on static residential patterns, often failing to capture the dynamic nature of social mixing at the neighborhood level. Leveraging high-resolution location-based data from mobile…

Public opinion surveys show cross-cultural differences in political opinions between socio-cultural contexts. However, there is no clear evidence whether these differences translate to cross-lingual differences in multilingual large…

Large Language Models (LLMs) have rapidly increased in size and apparent capabilities in the last three years, but their training data is largely English text. There is growing interest in multilingual LLMs, and various efforts are striving…

Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained…

Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit…

Existing urban boundaries are usually defined by government agencies for administrative, economic, and political purposes. Defining urban boundaries that consider socio-economic relationships and citizen commute patterns is important for…

As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for responsible AI deployment. Although bias assessment frameworks have…

The interaction between fringe subcultures and mainstream online communities poses significant challenges for understanding discourse on social media. In this work, we investigate whether users active in conspiracy-focused communities…

Multilingual studies of social bias in open-ended LLM generation remain limited: most existing benchmarks are English-centric, template-based, or restricted to recognizing pre-specified stereotypes. We introduce StereoTales, a multilingual…

With the advance of the Internet, ordinary users have created multiple personal accounts on online social networks, and interactions among these social network users have recently been tagged with location information. In this work, we…

Large language models are, by definition, based on language. In an effort to underscore the critical need for regional localized models, this paper examines primary differences between variants of written Spanish across Latin America and…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

Large-scale networks of human interaction, in particular country-wide telephone call networks, can be used to redraw geographical maps by applying algorithms of topological community detection. The geographic projections of the emerging…

Language models generally produce grammatical text, but they are more likely to make errors in certain contexts. Drawing on paradigms from psycholinguistics, we carry out a fine-grained analysis of those errors in different syntactic…

Many aspects of people's lives are proven to be deeply connected to their jobs. In this paper, we first investigate the distinct characteristics of major occupation categories based on tweets. From multiple social media platforms, we gather…

Slang is a commonly used type of informal language that poses a daunting challenge to NLP systems. Recent advances in large language models (LLMs), however, have made the problem more approachable. While LLM agents are becoming more widely…

Individuals involved in gang-related activity use mainstream social media including Facebook and Twitter to express taunts and threats as well as grief and memorializing. However, identifying the impact of gang-related activity in order to…

Even though the Internet and social media have increased the amount of news and information people can consume, most users are only exposed to content that reinforces their positions and isolates them from other ideological communities.…

Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing…