相关论文: "What is the value of {templates}?" Rethinking Doc…
Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding. Previous approaches…
Advances in the Visually-rich Document Understanding (VrDU) field and particularly the Key-Information Extraction (KIE) task are marked with the emergence of efficient Transformer-based approaches such as the LayoutLM models. Despite the…
Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive…
Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal large language models…
Document Key Information Extraction (KIE) is a technology that transforms valuable information in document images into structured data, and it has become an essential function in industrial settings. However, current evaluation metrics of…
In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy,…
Relevance evaluation of a query and a passage is essential in Information Retrieval (IR). Recently, numerous studies have been conducted on tasks related to relevance judgment using Large Language Models (LLMs) such as GPT-4, demonstrating…
Enterprise documents, such as forms and reports, embed critical information for downstream applications like data archiving, automated workflows, and analytics. Although generalist Vision Language Models (VLMs) perform well on established…
Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language models performance on retrieving and answering questions from documents, assessing the…
Information Extraction (IE) researchers are mapping tasks to Question Answering (QA) in order to leverage existing large QA resources, and thereby improve data efficiency. Especially in template extraction (TE), mapping an ontology to a set…
Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K)…
Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown…
Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper…
Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can…
With the advent of artificial intelligence (AI), many researchers are attempting to extract structured information from document-level biomedical literature by fine-tuning large language models (LLMs). However, they face significant…
Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by…
Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision…
Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we identify a critical limitation of such formatting: it induces a…
The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key…
Building document-grounded dialogue systems have received growing interest as documents convey a wealth of human knowledge and commonly exist in enterprises. Wherein, how to comprehend and retrieve information from documents is a…