Related papers: Documentation Practices of Artificial Intelligence

Related papers

DocClaw: A Unified Agentic System for Intelligent Document Processing [70.82545096015238]
We introduce DocClaw, a unified agentic system that formulates diverse intelligent document processing tasks as a shared process of interaction between an agent and a document.<n>Under this formulation, task-specific requirements are captured by the agent's interpretation of the query objective and the corresponding document skill.<n>Experiments across multiple intelligent document processing benchmarks demonstrate that DocClaw effectively handles diverse tasks within a single agentic framework.
arXiv Detail & Related papers (2026-08-19T08:34:48Z)
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations [106.74348504930124]
We introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy.<n>Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses.<n>Our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents.
arXiv Detail & Related papers (2026-07-22T07:52:59Z)
DocOS: Towards Proactive Document-Guided Actions in GUI Agents [54.27655693145045]
textbfDocOS is a benchmark designed to assess document-guided problem solving in fully interactive environments.<n>Experiments reveal that agents struggle to reliably locate relevant information during proactive search and frequently fail to faithfully ground retrieved instructions into precise actions.
arXiv Detail & Related papers (2026-05-18T08:36:04Z)
From Reflection to Repair: A Scoping Review of Dataset Documentation Tools [10.124271544484634]
We present a systematic review supported by mixed-methods analysis of 59 dataset documentation publications.<n>Our analysis shows four persistent patterns in dataset documentation conceptualization that potentially impede adoption and standardization.<n>Building on these findings, we propose a shift in Responsible AI tool design toward institutional rather than individual solutions.
arXiv Detail & Related papers (2026-02-17T19:37:16Z)
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
arXiv Detail & Related papers (2025-10-17T02:33:16Z)
Structured Attention Matters to Multimodal LLMs in Document Understanding [52.37530640460363]
We investigate how input format influences document comprehension performance.<n>We discover that raw OCR text often impairs rather than improves MLLMs' performance.<n>We propose a novel structure-preserving approach that encodes document elements using the LaTex paradigm.
arXiv Detail & Related papers (2025-06-19T07:16:18Z)
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models [58.45517851437422]
Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understanding. Existing solutions often rely on task-specific architectures and objectives for individual tasks. In this paper, we introduce Omni V2, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis.
arXiv Detail & Related papers (2025-02-22T09:32:01Z)
MuDoC: An Interactive Multimodal Document-grounded Conversational AI System [4.7191037525744735]
Building a multimodal document-grounded AI system to interact with long documents remains a challenge. We present an interactive conversational AI agent 'MuDoC' based on GPT-4o to generate document-grounded responses with interleaved text and figures.
arXiv Detail & Related papers (2025-02-14T01:05:51Z)
DocMIA: Document-Level Membership Inference Attacks against DocVQA Models [52.13818827581981]
We introduce two novel membership inference attacks tailored specifically to DocVQA models. Our methods outperform existing state-of-the-art membership inference attacks across a variety of DocVQA models and datasets.
arXiv Detail & Related papers (2025-02-06T00:58:21Z)
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions [60.733557487886635]
This paper focuses on bridging the comprehension gap between Large Language Models and external tools. We propose a novel framework, DRAFT, aimed at Dynamically refining tool documentation. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality.
arXiv Detail & Related papers (2024-10-10T17:58:44Z)
Unified Multi-Modal Interleaved Document Representation for Information Retrieval [57.65409208879344]
We produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities. Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation.
arXiv Detail & Related papers (2024-10-03T17:49:09Z)
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval [59.25292920967197]
Few-shot document entity retrieval (VDER) is an important topic in industrial NLP applications. FewVEX is a new dataset to boost future research in the field of entity-level few-shot VDER. We present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization.
arXiv Detail & Related papers (2023-11-01T17:51:43Z)
Workshop on Document Intelligence Understanding [3.2929609168290543]
This workshop aims to bring together researchers and industry developers in the field of document intelligence. We also released a data challenge on the recently introduced document-level VQA dataset, PDFVQA.
arXiv Detail & Related papers (2023-07-31T02:14:25Z)
Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering [49.85790367128085]
We pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. This novel multi-document QA formulation directs the model to better recover cross-text informational relations. Unlike prior multi-document models that focus on either classification or summarization tasks, our pre-training objective formulation enables the model to perform tasks that involve both short text generation and long text generation.
arXiv Detail & Related papers (2023-05-24T17:48:40Z)
Information Extraction from Documents: Question Answering vs Token Classification in real-world setups [0.0]
We compare the Question Answering approach with the classical token classification approach for document key information extraction. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach.
arXiv Detail & Related papers (2023-04-21T14:43:42Z)
HADES: Homologous Automated Document Exploration and Summarization [3.3509104620016092]
HADES is designed to streamline the work of professionals dealing with large volumes of documents. The tool employs a multi-step pipeline that begins with processing PDF documents using topic modeling, summarization, and analysis of the most important words for each topic.
arXiv Detail & Related papers (2023-02-25T15:16:10Z)
Unified Pretraining Framework for Document Understanding [52.224359498792836]
We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
arXiv Detail & Related papers (2022-04-22T21:47:04Z)
Document AI: Benchmarks, Models and Applications [35.46858492311289]
Document AI refers to the techniques for automatically reading, understanding, and analyzing business documents. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI. This paper briefly reviews some of the representative models, tasks, and benchmark datasets.
arXiv Detail & Related papers (2021-11-16T16:43:07Z)
Extracting Procedural Knowledge from Technical Documents [1.0773368566852943]
Procedures are an important knowledge component of documents that can be leveraged by cognitive assistants for automation, question-answering or driving a conversation. It is a challenging problem to parse big dense documents like product manuals, user guides to automatically understand which parts are talking about procedures and subsequently extract them.
arXiv Detail & Related papers (2020-10-20T09:47:52Z)
Explaining Relationships Between Scientific Documents [55.23390424044378]
We address the task of explaining relationships between two scientific documents using natural language text. In this paper we establish a dataset of 622K examples from 154K documents.
arXiv Detail & Related papers (2020-02-02T03:54:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.