相关论文: Scaling Accessible Mathematics on arXiv: HTML Conv…
In October 2023, arXiv made HTML formatted papers available to readers. This was the exciting outcome of over a year of accessibility research and development with the scientific community. Currently, only 2.4% of research outputs meet…
The research content hosted by arXiv is not fully accessible to everyone due to disabilities and other barriers. This matters because a significant proportion of people have reading and visual disabilities, it is important to our community…
The rise and growing popularity of accessible large language models have raised questions about their impact on various aspects of life, including how scientists write and publish their research. The primary objective of this paper is to…
Public universities in the US must now meet digital accessibility (DA) standards under 2024 updates to Title II of the ADA. For math instructors, course materials must be screen-reader parsable, which standard LaTeX-to-PDF workflows cannot…
Marked by the highlights of native generation of EPUB E-books and TikZ support for creating SVG images, we present an annual report of LaTeXML development in 2013. LaTeXML provides a reimplementation of the $\TeX$ parser, geared towards…
LaTeXML, a $\TeX$ to XML converter, is being used in a wide range of MKM applications. In this paper, we present a progress report for the 2012 calendar year. Noteworthy enhancements include: increased coverage such as Wikipedia syntax;…
Large language model (LLM) research has grown rapidly, along with increasing concern about their limitations. In this survey, we conduct a data-driven, semi-automated review of research on limitations of LLMs (LLLMs) from 2022 to early 2025…
In this work, we study how URL extraction results depend on input format. We compiled a pilot dataset by extracting URLs from 10 arXiv papers and used the same heuristic method to extract URLs from four formats derived from the PDF files or…
arXiv is the largest open-access repository for scientific literature. When submitting a paper, authors upload the manuscript's source files, from which the final PDF is compiled. These source files are also publicly downloadable,…
Screen-reader software enables blind users to access large segments of electronic content, particularly if accessibility standards are followed. Unfortunately, this is not true for much of the content written in physics, mathematics, and…
There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model…
Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and…
This draft is a working document, having a summary of nighty-four (94) papers with additional sections on Traceability of Software Requirements (Section 4), Formal Methods and Its Tools (Section 5), Unifying Theories of Programming (UTP)…
Making scientific papers accessible may require reprocessing old papers to create output compliant with accessibility standards. An important step there is to convert the visual formatting to the logical one. In this report we describe our…
Based on one million arXiv papers submitted from May 2018 to January 2024, we assess the textual density of ChatGPT's writing style in their abstracts through a statistical analysis of word frequency changes. Our model is calibrated and…
As part of its 25th anniversary vision-setting process, the arXiv team at Cornell University Library conducted a user survey in April 2016 to seek input from the global user community about arXiv's current services and future directions. We…
Today's peer review process for scientific articles is unnecessarily opaque and offers few incentives to referees. Likewise, the publishing process is unnecessarily inefficient and its results are only rarely made freely available to the…
Preprints are essential for the timely and open dissemination of research. arXiv, the most widely used preprint service, takes the idea of open science one step further by not only publishing the actual preprints but also LaTeX sources and…
Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can ingest these documents at scale and make their content…
The paper presents and compares a range of parsers with and without data mapping for conversion between XML and Haskell. The best performing parser competes favorably with the fastest tools available in other languages and is, thus,…