Search Results for author:
Found 21 papers, 15 papers with code
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field.
Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective
Using the Graphusion-constructed KG, we achieve a significant improvement on the benchmark, for example, a 9. 2% accuracy improvement on sub-graph completion.
Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Education
Specifically, we introduce TutorQA, a new expert-verified benchmark for graph reasoning and QA, comprising six tasks and a total of 1, 200 QA pairs.
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding
Recently, many studies have demonstrated that exclusively incorporating OCR-derived text and spatial layouts with large language models (LLMs) can be highly effective for document understanding tasks.
What Makes Good Few-shot Examples for Vision-Language Models?
Despite the notable advancements achieved by leveraging pre-trained vision-language (VL) models through few-shot tuning for downstream tasks, our detailed empirical study highlights a significant dependence of few-shot learning outcomes on the careful selection of training examples - a facet that has been previously overlooked in research.
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding.
Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education
We assess LLMs' zero-shot performance in creating domain-specific concept graphs and introduce TutorQA, a new expert-verified NLP-focused benchmark for scientific graph reasoning and QA.
VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization
This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning.
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs).
What Large Language Models Bring to Text-rich VQA?
This pipeline achieved superior performance compared to the majority of existing Multimodal Large Language Models (MLLM) on four text-rich VQA datasets.
Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts
Educational materials such as survey articles in specialized fields like computer science traditionally require tremendous expert inputs and are therefore expensive to create and update.
UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and rich world knowledge inherent to these large pre-trained models, and the beneficial connections among tasks within the context of text-rich scenarios have not been sufficiently explored.
Deeply Coupled Cross-Modal Prompt Learning
Recent advancements in multimodal foundation models (e. g., CLIP) have excelled in zero-shot generalization.
PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets
In this work, we present a ``versatile'' model -- the Prompting-based Unified NER system (PUnifiedNER) -- that works with data from different domains and can recognise up to 37 entity types simultaneously, and theoretically it could be as many as possible.
SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning
Contrastive learning has recently achieved compelling performance in unsupervised sentence representation.
What Makes Pre-trained Language Models Better Zero-shot Learners?
Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori.
A Rationale-Centric Framework for Human-in-the-loop Machine Learning
We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios.
A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data
While with the recent emergence of BERT, deep learning language models can achieve reasonably good performance in document classification with few labelled instances, there is a lack of evidence in the utility of applying BERT-like models on long document classification.
Diverging Divergences: Examining Variants of Jensen Shannon Divergence for Corpus Comparison Tasks
Jensen-Shannon divergence (JSD) is a distribution similarity measurement widely used in natural language processing.
Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets
While simple vector representations such as bag-of-words and embedding-based representations based on techniques such as word2vec have been shown to be an effective way to represent documents during active learning, the emergence of representation mechanisms based on the pre-trained transformer-based neural network models popular in natural language processing research (e. g. BERT) offer a promising, and as yet not fully explored, alternative.
Investigating the Effectiveness of Representations Based on Word-Embeddings in Active Learning for Labelling Text Datasets
Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them.
