English
Related papers

Related papers: LATTE: Improving Latex Recognition for Tables and …

200 papers

Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source. Meanwhile, existing benchmarks for scientific document retrieval, such as ArXivQA…

Information Retrieval · Computer Science 2026-04-21 Ghazal Khalighinejad , Raghuveer Thirukovalluru , Alexander H. Oh , Bhuwan Dhingra

Document-level Information Extraction (DocIE) aims to produce an output template with the entities, relations, and events of interest occurring in the given document. Standard practices include prompting decoder-only LLMs using greedy…

Computation and Language · Computer Science 2026-05-29 Mikel Zubillaga , Oscar Sainz , Oier Lopez de Lacalle , Eneko Agirre

Tables present important information concisely in many scientific documents. Visual features like mathematical symbols, equations, and spanning cells make structure and content extraction from tables embedded in research documents…

Information Retrieval · Computer Science 2021-11-12 Pratik Kayal , Mrinal Anand , Harsh Desai , Mayank Singh

Knowledge editing aims to correct outdated or inaccurate knowledge in neural networks. In this paper, we explore knowledge editing using easily accessible documents instead of manually labeled factual triples employed in earlier research.…

Computation and Language · Computer Science 2025-07-25 Suhang Wu , Ante Wang , Minlong Peng , Yujie Lin , Wenbo Li , Mingming Sun , Jinsong Su

Recent deep learning approaches in table detection achieved outstanding performance and proved to be effective in identifying document layouts. Currently, available table detection benchmarks have many limitations, including the lack of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Mrinal Haloi , Shashank Shekhar , Nikhil Fande , Siddhant Swaroop Dash , Sanjay G

Despite the ubiquity of visualization examples published on the web, retargeting existing custom chart implementations to new datasets remains difficult, time-intensive, and tedious. The adaptation process assumes author familiarity with…

Human-Computer Interaction · Computer Science 2026-01-21 Luke S. Snyder , Chenglong Wang , Steven M. Drucker

Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches…

Computation and Language · Computer Science 2025-10-01 Xiaohan Yu , Pu Jian , Chong Chen

Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task,…

Machine Learning · Computer Science 2025-08-22 Vishnou Vinayagame , Gregory Senay , Luis Martí

This paper presents an experience report on the development of Retrieval Augmented Generation (RAG) systems using PDF documents as the primary data source. The RAG architecture combines generative capabilities of Large Language Models…

Software Engineering · Computer Science 2024-10-22 Ayman Asad Khan , Md Toufique Hasan , Kai Kristian Kemell , Jussi Rasku , Pekka Abrahamsson

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…

Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or…

Computation and Language · Computer Science 2024-06-06 Tianjun Zhang , Shishir G. Patil , Naman Jain , Sheng Shen , Matei Zaharia , Ion Stoica , Joseph E. Gonzalez

Printed mathematical expression recognition (MER) models are usually trained and tested using LaTeX-generated mathematical expressions (MEs) as input and the LaTeX source code as ground truth. As the same ME can be generated by various…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Felix M. Schmitt-Koopmann , Elaine M. Huang , Hans-Peter Hutter , Thilo Stadelmann , Alireza Darvishy

First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection. While existing retrieval models have achieved impressive performance, they are mostly studied on static data sets,…

Information Retrieval · Computer Science 2023-08-23 Yinqiong Cai , Keping Bi , Yixing Fan , Jiafeng Guo , Wei Chen , Xueqi Cheng

The table reasoning task aims to answer the question according to the given table. Currently, using Large Language Models (LLMs) is the predominant method for table reasoning. Most existing methods employ a fixed tabular format to represent…

Computation and Language · Computer Science 2024-08-28 Xuanliang Zhang , Dingzirui Wang , Longxu Dou , Baoxin Wang , Dayong Wu , Qingfu Zhu , Wanxiang Che

Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions…

Computation and Language · Computer Science 2023-06-21 Haotian Chen , Bingsheng Chen , Xiangdong Zhou

Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failures and curate the training evidence needed to correct them. Late-interaction models such as…

Information Retrieval · Computer Science 2026-04-22 François Remy

Representing the parton distribution functions (PDFs) of the proton and other hadrons through flexible, high-fidelity parametrizations has been a long-standing goal of particle physics phenomenology. This is particularly true since the…

High Energy Physics - Phenomenology · Physics 2024-06-21 Brandon Kriesten , T. J. Hobbs

Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text. However, in many…

Computation and Language · Computer Science 2023-02-14 Zhichao Duan , Xiuxing Li , Zhenyu Li , Zhuo Wang , Jianyong Wang

The conventional use of the Retrieval-Augmented Generation (RAG) architecture has proven effective for retrieving information from diverse documents. However, challenges arise in handling complex table queries, especially within PDF…

Machine Learning · Computer Science 2024-02-13 Uday Allu , Biddwan Ahmed , Vishesh Tripathi

Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. To better evaluate this setting and facilitate modeling efforts, we introduce TACT - Text And Calculations through…

Computation and Language · Computer Science 2024-10-15 Avi Caciularu , Alon Jacovi , Eyal Ben-David , Sasha Goldshtein , Tal Schuster , Jonathan Herzig , Gal Elidan , Amir Globerson
‹ Prev 1 3 4 5 6 7 10 Next ›