This paper introduces CommonForms, a web-scale dataset for form field detection. It casts the problem of form field detection as object detection: given an image of a page, predict the location and type (Text Input, Choice Button, Signature) of form fields. The dataset is constructed by filtering Common Crawl to find PDFs that have fillable elements. Starting with 8 million documents, the filtering process is used to arrive at a final dataset of roughly 55k documents that have over 450k pages. Analysis shows that the dataset contains a diverse mixture of languages and domains; one third of the pages are non-English, and among the 14 classified domains, no domain makes up more than 25% of the dataset. In addition, this paper presents a family of form field detectors, FFDNet-Small and FFDNet-Large, which attain a very high average precision on the CommonForms test set. Each model cost less than $500 to train. Ablation results show that high-resolution inputs are crucial for high-quality form field detection, and that the cleaning process improves data efficiency over using all PDFs that have fillable fields in Common Crawl. A qualitative analysis shows that they outperform a popular, commercially available PDF reader that can prepare forms. Unlike the most popular commercially available solutions, FFDNet can predict checkboxes in addition to text and signature fields. This is, to our knowledge, the first large scale dataset released for form field detection, as well as the first open source models. The dataset, models, and code will be released at https://github.com/jbarrow/commonforms

PDFs have long been the digital equivalent of a necessary chore: tedious, clunky, and often frustrating. But UPDF 2.0 flips the script, turning document work into something surprisingly smooth and efficient, and you don't have to pay a monthly subscription to get it. Right now, lifetime access to UPDF is just 59.99, a sharp 60 percent discount from the usual 149.99. Heads up: this deal is only for new users, and if you're eyeing UPDF's futuristic AI add-on, that's not included in the lifetime package--you'll have to grab it separately from UPDF.com. UPDF runs seamlessly across Windows, macOS, iOS, and Android, so whether you're on your laptop, phone, or tablet, your PDFs are always within reach.

Acrobat Pro's comprehensive PDF features show why it's still the editor against which all others are judged. Editor's note: This review was updated December 9, 2024 to reflect the addition of AI Assistant and current pricing. Adobe created the PDF two decades ago and its PDF editor has continued to rule the category, despite what many users felt was its exorbitant price. But a couple of years back, Acrobat adopted a cloud subscription model that now makes it more affordable for folks without an enterprise budget. Acrobat Pro is composed of three components: Acrobat, which allows you to perform a variety of editing functions on your PDFs on desktop and mobile devices; Adobe Document Cloud, which lets you create and export PDF files, as well as store and send files and collect electronic signatures; and Acrobat Reader, which enables you to read, print, and sign PDFs.

Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs). However, accurately assessing the performance of these applications remains a challenge, mainly due to the lack of suitable benchmarks that effectively simulate real-world scenarios. To address this challenge, we introduce two product question-answering (QA) datasets focused on Adobe Acrobat and Photoshop products to help evaluate the performance of existing models on domain-specific product QA tasks. Additionally, we propose a novel knowledge-driven RAG-QA framework to enhance the performance of the models in the product QA task. Our experiments demonstrated that inducing domain knowledge through query reformulation allowed for increased retrieval and generative performance when compared to standard RAG-QA methods. This improvement, however, is slight, and thus illustrates the challenge posed by the datasets introduced.