18 citations · 71 across the 19 of their papers we have counts for
19 papers
CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation
Santosh T. Y. S. S, Youssef Tarek Elkhayat, Oana Ichim +5
Due to their ability to process long and complex contexts, LLMs can offer key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfai…
-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation
Zhen Wu, Ritam Dutt, Luke M. Breitfeller +3
Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual comp…
Where is this coming from? Making groundedness count in the evaluation of Document VQA models
Armineh Nourbakhsh, Siddharth Parekh, Pranav Shetty +3
Document Visual Question Answering (VQA) models have evolved at an impressive rate over the past few years, coming close to or matching human performance on some benchmarks. We arg…
"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
Ran Zmigrod, Pranav Shetty, Mathieu Sibue +4
The rise of large language models (LLMs) for visually rich document understanding (VRDU) has kindled a need for prompt-response, document-based datasets. As annotating new datasets…
A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law
Zhiyu Zoey Chen, Jing Ma, Xinlu Zhang +7
In the fast-evolving domain of artificial intelligence, large language models (LLMs) such as GPT-3 and GPT-4 are revolutionizing the landscapes of finance, healthcare, and law: dom…
BuDDIE: A Business Document Dataset for Multi-task Information Extraction
Ran Zmigrod, Dongsheng Wang, Mathieu Sibue +10
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 spec…
Belief and Persuasion in Scientific Discourse on Social Media: A Study of the COVID-19 Pandemic
Salwa Alamir, Armineh Nourbakhsh, Cecilia Tilli +2
Research into COVID-19 has been rapidly evolving since the onset of the pandemic. This occasionally results in contradictory recommendations by credible sources of scientific opini…
TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing
Ran Zmigrod, Zhiqiang Ma, Armineh Nourbakhsh +1
Visually Rich Form Understanding (VRFU) poses a complex research problem due to the documents' highly structured nature and yet highly variable style and content. Current annotatio…
DocGraphLM: Documental Graph Language Model for Information Extraction
Dongsheng Wang, Zhiqiang Ma, Armineh Nourbakhsh +2
Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures…
The Influence of Biomedical Research on Future Business Funding: Analyzing Scientific Impact and Content in Industrial Investments
Reza Khanmohammadi, Simerjot Kaur, Charese H. Smiley +4
This paper investigates the relationship between scientific innovation in biomedical sciences and its impact on industrial activities, focusing on how the historical impact and con…
DocLLM: A layout-aware generative language model for multimodal document understanding
Dongsheng Wang, Natraj Raman, Mathieu Sibue +6
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalit…
Parameterized Explanations for Investor / Company Matching
Simerjot Kaur, Ivan Brugere, Andrea Stefanucci +3
Matching companies and investors is usually considered a highly specialized decision making process. Building an AI agent that can automate such recommendation process can signific…
A Framework for Institutional Risk Identification using Knowledge Graphs and Automated News Profiling
Mahmoud Mahfouz, Armineh Nourbakhsh, Sameena Shah
Organizations around the world face an array of risks impacting their operations globally. It is imperative to have a robust risk identification process to detect and evaluate the…
Robust Document Representations using Latent Topics and Metadata
Natraj Raman, Armineh Nourbakhsh, Sameena Shah +1
Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification prob…
SPot: A tool for identifying operating segments in financial tables
Zhiqiang Ma, Steven Pomerville, Mingyang Di +1
In this paper we present SPot, an automated tool for detecting operating segments and their related performance indicators from earnings reports. Due to their company-specific natu…
A framework for anomaly detection using language modeling, and its applications to finance
Armineh Nourbakhsh, Grace Bang
In the finance sector, studies focused on anomaly detection are often associated with time-series and transactional data analytics. In this paper, we lay out the opportunities for…
Reuters Tracer: Toward Automated News Production Using Large Scale Social Media Data
Xiaomo Liu, Armineh Nourbakhsh, Quanzhi Li +3
To deal with the sheer volume of information and gain competitive advantage, the news industry has started to explore and invest in news automation. In this paper, we present Reute…
"Breaking" Disasters: Predicting and Characterizing the Global News Value of Natural and Man-made Disasters
Armineh Nourbakhsh, Quanzhi Li, Xiaomo Liu +1
Due to their often unexpected nature, natural and man-made disasters are difficult to monitor and detect for journalists and disaster management response teams. Journalists are inc…
Data Sets: Word Embeddings Learned from Tweets and General Data
Quanzhi Li, Sameena Shah, Xiaomo Liu +1
A word embedding is a low-dimensional, dense and real- valued vector representation of a word. Word embeddings have been used in many NLP tasks. They are usually gener- ated from a…