12 citations · 54 across the 20 of their papers we have counts for
20 papers
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang, Zifeng Wang, Long Le +9
Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date respo…
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
Letian Peng, Zilong Wang, Feng Yao +2
Information extraction (IE) is a fundamental area in natural language processing where prompting large language models (LLMs), even with in-context examples, cannot defeat small LM…
DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
Alex Nguyen, Zilong Wang, Jingbo Shang +1
The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists i…
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
Letian Peng, Yuwei Zhang, Zilong Wang +4
This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embedding…
Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
Li Zhong, Zilong Wang, Jingbo Shang
Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers i…
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Zilong Wang, Hao Zhang, Chun-Liang Li +8
Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verificat…
EmojiLM: Modeling the New Emoji Language
Letian Peng, Zilong Wang, Hang Liu +2
With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content. The increasing usage of emoji becomes a noti…
LMDX: Language Model-based Document Information Extraction and Localization
Vincent Perot, Kai Kang, Florian Luisier +9
Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, th…
Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
Li Zhong, Zilong Wang
Recently, the large language models (LLMs) have shown extraordinary ability in understanding natural language and generating programming code. It has been a common practice of soft…
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
Zilong Wang, Jingbo Shang
The rapid growth of web pages and the increasing complexity of their structure poses a challenge for web mining models. Web mining models are required to understand the semi-struct…
Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation
Prashant Krishnan, Zilong Wang, Yangkun Wang +1
Recent advances of incorporating layout information, typically bounding box coordinates, into pre-trained language models have achieved significant performance in entity recognitio…
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Zilong Wang, Jiuxiang Gu, Chris Tensmeyer +5
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g…
VRDU: A Benchmark for Visually-rich Document Understanding
Zilong Wang, Yichao Zhou, Wei Wei +2
Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recen…
Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition
Zihan Wang, Kewen Zhao, Zilong Wang +1
Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks. We argue that under the few-shot…
Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
Zilong Wang, Jingbo Shang
Entity recognition is a fundamental task in understanding document images. Traditional sequence labeling frameworks treat the entity types as class IDs and rely on extensive data a…
LayoutReader: Pre-training of Text and Layout for Reading Order Detection
Zilong Wang, Yiheng Xu, Lei Cui +2
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep lear…
GroupLink: An End-to-end Multitask Method for Word Grouping and Relation Extraction in Form Understanding
Zilong Wang, Mingjie Zhan, Houxing Ren +4
Forms are a common type of document in real life and carry rich information through textual contents and the organizational structure. To realize automatic processing of forms, wor…
DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding
Zilong Wang, Mingjie Zhan, Xuebo Liu +1
Form understanding depends on both textual contents and organizational structure. Although modern OCR performs well, it is still challenging to realize general form understanding b…
Exploring Semantic Capacity of Terms
Jie Huang, Zilong Wang, Kevin Chen-Chuan Chang +2
We introduce and study semantic capacity of terms. For example, the semantic capacity of artificial intelligence is higher than that of linear regression since artificial intellige…
TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
Zilong Wang, Zhaohong Wan, Xiaojun Wan
Multimodal sentiment analysis is an important research area that predicts speaker's sentiment tendency through features extracted from textual, visual and acoustic modalities. The…