Related papers: Synthetic Document Question Answering in Hungarian

Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and…

Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while…

Acquiring high-quality knowledge is a central focus in Knowledge-Based Visual Question Answering (KB-VQA). Recent methods use large language models (LLMs) as knowledge engines for answering. These methods generally employ image captions as…

Text Simplification is a task that has been minimally explored for low-resource languages. Consequently, there are only a few manually curated datasets. In this paper, we present a human curated sentence-level text simplification dataset…

Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for…

Automated document layout analysis remains a major challenge for low-resource, non-Latin scripts. Khmer is a language spoken daily by over 17 million people in Cambodia, receiving little attention in the development of document AI tools.…

Knowledge-based Visual Question Answering (KVQA) tasks require answering questions about images using extensive background knowledge. Despite significant advancements, generative models often struggle with these tasks due to the limited…

With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus. However, existing retrieval systems…

With the rapid advancement of natural language processing (NLP) technologies, the demand for high-quality Chinese document question-answering datasets is steadily growing. To address this issue, we present the Chinese Multi-Document…

The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality…

Visual Question Answering (VQA) research seeks to create AI systems to answer natural language questions in images, yet VQA methods often yield overly simplistic and short answers. This paper aims to advance the field by introducing Visual…

We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 trillion tokens, this is likely the largest generally available multilingual collection of LLM…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

We study the problem of completing various visual document understanding (VDU) tasks, e.g., question answering and information extraction, on real-world documents through human-written instructions. To this end, we propose InstructDoc, the…

Visual Question Answering (VQA) is a challenging task that requires the joint understanding of natural language and visual content. While early research primarily focused on recognizing objects and scene context, it often overlooked scene…

Document Understanding (DU) in long-contextual scenarios with complex layouts remains a significant challenge in vision-language research. Although Large Vision-Language Models (LVLMs) excel at short-context DU tasks, their performance…

With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence. However, the most popular datasets used to evaluate MLLMs are…

Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly…

Document Visual Question Answering (DocVQA) models often produce overconfident or ethically misaligned responses, especially under uncertainty. Existing models like LayoutLMv3, UDOP, and DONUT focus on accuracy but lack ethical calibration.…

The advent and proliferation of large multi-modal models (LMMs) have introduced new paradigms to computer vision, transforming various tasks into a unified visual question answering framework. Video Quality Assessment (VQA), a classic field…