相关论文: Should Corpora be Big, Rich, or Dense?

Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing…

The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks…

Compositional understanding is crucial for human intelligence, yet it remains unclear whether contemporary vision models exhibit it. The dominant machine learning paradigm is built on the premise that scaling data and model sizes will…

We discuss how desirable it is that Large Language Models (LLMs) be able to adapt or align their language behavior with users who may be diverse in their language use. User diversity may come about among others due to i) age differences;…

This study reviewed the use of Large Language Models (LLMs) in healthcare, focusing on their training corpora, customization techniques, and evaluation metrics. A systematic search of studies from 2021 to 2024 identified 61 articles. Four…

Chat-based large language models have the opportunity to empower individuals lacking high-quality healthcare access to receive personalized information across a variety of topics. However, users may ask underspecified questions that require…

Accounting for resources is the central issue in computational efficiency. We point out physical constraints implicit in information readout that have been overlooked in classical computing. The basic particle-counting mode of read-out sets…

The process of debating is essential in our daily lives, whether in studying, work activities, simple everyday discussions, political debates on TV, or online discussions on social networks. The range of uses for debates is broad. Due to…

To date, the bulk of research on single-channel speech separation has been conducted using clean, near-field, read speech, which is not representative of many modern applications. In this work, we develop a procedure for constructing…

Chatbots have shown promise as tools to scale qualitative data collection. Recent advances in Large Language Models (LLMs) could accelerate this process by allowing researchers to easily deploy sophisticated interviewing chatbots. We test…

Catalogues of galaxies, clusters of galaxies and superclusters - sources of information to study the large-scale structure of the Universe are reviewed. The power spectrum of density perturbations, and the correlation function are discussed…

This paper presents novel systems and methodologies for the development of efficient large language models (LLMs). It explores the trade-offs between model size, performance, and computational resources, with the aim of maximizing the…

Large Language Models (LLMs) are distinguished by their architecture, which dictates their parameter size and performance capabilities. Social scientists have increasingly adopted LLMs for text classification tasks, which are difficult to…

Large information sizes in samples and features can be encoded to speed up the learning of statistical models based on linear algebra and remove unwanted signals. Encoding information can reduce both sample and feature dimension to a…

Regulatory functions are essential in both socioeconomic and biological systems, from corporate managers to regulatory genes. Regulatory functions come with substantial costs and benefits, and the balance of the two is often taken for…

Understanding how growth induces form is a longstanding biological question. Many studies concentrated on the shapes of plant cells, fungi or bacteria. Some others have shown the importance of the mechanical properties of bacterial walls…

Qualitative researchers use tools to collect, sort, and analyze their data. Should qualitative researchers use large language models (LLMs) as part of their practice? LLMs could augment qualitative research, but it is unclear if their use…

Large language models (LLMs) represent a new paradigm for processing unstructured data, with applications across an unprecedented range of domains. In this paper, we address, through two arguments, whether the development and application of…

Robust statistics aims to compute quantities to represent data where a fraction of it may be arbitrarily corrupted. The most essential statistic is the mean, and in recent years, there has been a flurry of theoretical advancement for…

When dealing with subjective, noisy, or otherwise nebulous features, the "wisdom of crowds" suggests that one may benefit from multiple judgments of the same feature on the same object. We give theoretically-motivated `feature…