Related papers: Scaling Accessible Mathematics on arXiv: HTML Conv…
Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are promising, the broader effects of such application and their integration into real-world…
Language models have been effective in a wide range of applications, yet the most sophisticated models are often proprietary. For example, GPT-4 by OpenAI and various models by Anthropic are expensive and consume substantial energy. In…
The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and…
Users demand fast, seamless webpage experiences, yet developers often struggle to meet these expectations within tight constraints. Performance optimization, while critical, is a time-consuming and often manual process. One of the most…
Achieving web accessibility is essential to building inclusive digital experiences. However, accessibility issues are often identified only after a website has been fully developed, making them difficult to address. This paper introduces a…
Commercial ML APIs offered by providers such as Google, Amazon and Microsoft have dramatically simplified ML adoption in many applications. Numerous companies and academics pay to use ML APIs for tasks such as object detection, OCR and…
There has been a considerable amount of research aimed at automating the documentation of accessibility in the built environment. Yet so far, there has been no fully automatic system that has been shown to reliably document surface quality…
Web accessibility ensures that individuals with disabilities can access and interact with digital content without barriers, yet a significant majority of most used websites fail to meet accessibility standards. This study evaluates…
The success of Large Language Models (LLMs) in other domains has raised the question of whether LLMs can reliably assess and manipulate the readability of text. We approach this question empirically. First, using a published corpus of 4,724…
We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We…
We mark up a corpus of LaTeX lecture notes semantically and expose them as Linked Data in XHTML+MathML+RDFa. Our application makes the resulting documents interactively browsable for students. Our ontology helps to answer queries from…
We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning. Using a dataset of over 200 language model evaluations on Wikitext and Penn Treebank spanning 2012-2023, we find…
Mathematical reasoning continues to be a critical challenge in large language model (LLM) development with significant interest. However, most of the cutting-edge progress in mathematical reasoning with LLMs has become \emph{closed-source}…
The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics, and artificial intelligence. Despite these advancements,…
Traditionally, mathematical knowledge is published in printed media such as books or journals. With the advent of the Internet, a new method of publication became available. To date, however, most online mathematical publications do not…
An inclusive science, technology, engineering and mathematics (STEM) workforce is needed to maintain America's leadership in the scientific enterprise. Increasing the participation of underrepresented groups in STEM, including persons with…
While web data quality is crucial for large language models, most curation efforts focus on filtering and deduplication,treating HTML-to-text extraction as a fixed pre-processing step. Existing web corpora rely on heuristic-based extractors…
The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on…
Training summarization models requires substantial amounts of training data. However for less resourceful languages like Hungarian, openly available models and datasets are notably scarce. To address this gap our paper introduces HunSum-2…
Computational reproducibility is central to scientific credibility, yet verifying published results at scale remains costly. We develop an AI-assisted workflow for automated full-paper replication -- retrieving materials, reconstructing…