Related papers: LATTE: Improving Latex Recognition for Tables and …
Tables are among the most widely used tools for representing structured data in research, business, medicine, and education. Although LLMs demonstrate strong performance in downstream tasks, their efficiency in processing tabular data…
We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics. To this end, we modify the Transformer encoder architecture in a way that allows it to use layout features…
Document layout analysis involves understanding the arrangement of elements within a document. This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings. The…
As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval. Previously, an effective…
How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high…
Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective…
Improving data quality in unstructured documents is a long-standing challenge. Unstructured data, especially in textual form, inherently lacks defined semantics, which poses significant challenges for effective processing and for ensuring…
Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…
Tabulated content is omnipresent in scientific literature. This work presents the R package *tableParser*, designed to extract and postprocess tables from NISO-JATS-encoded XML, HTML, DOCX, and, with limitations, PDF documents.…
Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…
LLMssuch as GPT-4 have shown a remarkable ability to solve complex questions by generating step-by-step rationales. Prior works have utilized this capability to improve smaller and cheaper LMs (say, with 7B parameters). However, various…
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and…
Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is computationally…
With the rapid development of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) has become a predominant method in the field of professional knowledge-based question answering. Presently, major foundation model companies…
Diffusion large language models (dLLMs) are emerging as a compelling alternative to dominant autoregressive models, replacing strictly sequential token generation with iterative denoising and parallel generation dynamics. However, their…
The latest developments in Natural Language Processing (NLP) have demonstrated remarkable progress in a code-text retrieval problem. As the Transformer-based models used in this task continue to increase in size, the computational costs and…
Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and…
The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this…
Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream information extraction from…