Related papers: Breaking the Code: Multi-level Learning in the Eur…
Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly prevalent in online content, where users naturally mix…
Children can use the statistical regularities of their environment to learn word meanings, a mechanism known as cross-situational learning. We take a computational approach to investigate how the information present during each observation…
A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic…
This innovative practice article reports on the piloting of vibe coding (using natural language to create software applications with AI) for English as a Foreign Language (EFL) education. We developed a human-AI meta-languaging framework…
State-of-the-art results in typical classification tasks are mostly achieved by unexplainable machine learning methods, like deep neural networks, for instance. Contrarily, in this paper, we investigate the application of rule learning…
Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly must be better at assembling facts. We show that this…
Do projects learn across space and time? The Olympics, among the largest publicly funded programmes in the world, offer a unique empirical setting. Theoretically, the Games seem ideal for generating "positive learning curves," driving down…
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the…
In recent times, we have seen an increased use of text chat for communication on social networks and smartphones. This particularly involves the use of Hindi-English code-mixed text which contains words which are not recognized in English…
Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more…
Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work, we introduce x1, a family of reasoning models that can…
National research evaluation exercises provide a comparative measure of research performance of the nation's institutions, and as such represent a tool for stimulating research productivity, particularly if the results are used to inform…
Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching…
Economic competition between humans leads to income inequality, but, so far, there has been little understanding of underlying quantitative mechanisms governing such a collective behavior. We analyze datasets of household income from 67…
Propaganda is a form of communication intended to influence the opinions and the mindset of the public to promote a particular agenda. With the rise of social media, propaganda has spread rapidly, leading to the need for automatic…
Multi-party linguistic entrainment refers to the phenomenon that speakers tend to speak more similarly during conversation. We first developed new measures of multi-party entrainment on features describing linguistic style, and then…
Gender discrimination in the hiring process is one significant factor contributing to labor market disparities. However, there is little evidence on the extent to which gender bias by hiring managers is responsible for these disparities. In…
We study the problem of online learning in competitive settings in the context of two-sided matching markets. In particular, one side of the market, the agents, must learn about their preferences over the other side, the firms, through…
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…