A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks

CX Liang, P Tian, CH Yin, Y Yua, W An-Hou… - arXiv preprint arXiv …, 2024 - arxiv.org
This survey and application guide to multimodal large language models (MLLMs) explores
the rapidly developing field of MLLMs, examining their architectures, applications, and …

A Survey on Data Synthesis and Augmentation for Large Language Models

K Wang, J Zhu, M Ren, Z Liu, S Li, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
The success of Large Language Models (LLMs) is inherently linked to the availability of vast,
diverse, and high-quality data for training and evaluation. However, the growth rate of high …

LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?

J Cegin, J Simko, P Brusilovsky - arXiv preprint arXiv:2408.16502, 2024 - arxiv.org
The generative large language models (LLMs) are increasingly being used for data
augmentation tasks, where text samples are LLM-paraphrased and then used for classifier …

LLM-DER: A Named Entity Recognition Method Based on Large Language Models for Chinese Coal Chemical Domain

L Xiao, Y Xu, J Zhao - arXiv preprint arXiv:2409.10077, 2024 - arxiv.org
Domain-specific Named Entity Recognition (NER), whose goal is to recognize domain-
specific entities and their categories, provides an important support for constructing domain …

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation

B Pecher, J Cegin, R Belanec, J Simko, I Srba… - arXiv preprint arXiv …, 2024 - arxiv.org
While fine-tuning of pre-trained language models generally helps to overcome the lack of
labelled training samples, it also displays model performance instability. This instability …

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification

J Cegin, B Pecher, J Simko, I Srba, M Bielikova… - arXiv preprint arXiv …, 2024 - arxiv.org
The generative large language models (LLMs) are increasingly used for data augmentation
tasks, where text samples are paraphrased (or generated anew) and then used for classifier …

Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment

C Dou, Y Zhang, Z Jin, W Jiao, H Zhao, Y Zhao… - arXiv preprint arXiv …, 2024 - arxiv.org
This research examines the use of Reinforcement Learning from AI Feedback (RLAIF)
techniques to improve healthcare dialogue models, with the aim of tackling the challenges of …