Bag of Lies: Robustness in Continuous Pre-training BERT

I Gevers, W Daelemans - arxiv preprint arxiv:2406.09967, 2024 - arxiv.org
This study aims to acquire more insights into the continuous pre-training phase of BERT
regarding entity knowledge, using the COVID-19 pandemic as a case study. Since the …

Global-Pruner: A Stable and Efficient Pruner for Retraining-Free Pruning of Encoder-Based Language Models

G Yao, Y Wang, H Xu, L Zhang… - Proceedings of the 28th …, 2024 - aclanthology.org
Large language models (LLMs) have achieved significant success in complex tasks across
various domains, but they come with high computational costs and inference latency issues …

Machine translation meets large language models: Evaluating ChatGPT's ability to automatically post-edit literary texts

L Macken - Proceedings of the 1st Workshop on Creative-text …, 2024 - aclanthology.org
Large language models such as GPT-4 have been trained on vast corpora, giving them
excellent language understanding. This study explores the use of ChatGPT for post-editing …

[PDF][PDF] Artificial Intelligence Shows Human-like Lens Capability in Subjectivity: Evaluating Chinese Pragmatic Capability of GPT-4 via Microsoft Copilot with Direct …

D Su, K Goslar - Exploring artificial intelligence in applied …, 2024 - iastatedigitalpress.com
For Artificial Intelligence (AI) to understand human input and generate output that is
ergonomic to humans, AI-generated language must demonstrate human-like capabilities in …

AI in Smart Tourism: LLMs & GPTs Leading the Way

A Kontogianni, E Alepis - 2024 15th International Conference …, 2024 - ieeexplore.ieee.org
The rise of Artificial Intelligence (AI) has dramatically transformed various industries,
including healthcare, finance, education, and transportation, with Large Language Models …

[PDF][PDF] MASTERARBEIT| MASTER'S THESIS

K Niederreiter - 2024 - phaidra.univie.ac.at
The exponential growth of the social media user base has led to an alarming rise in the use
of offensive language and profanity, necessitating effective detection mechanisms. This …

Sumarização de texto em Deep Learning como etapa inicial para a construção de um modelo de recuperação da informação: análise do setor de mineração no Brasil

LC de Jesus Falcão - 2024 - repositorio.ufmg.br
Na virada do século XX para o XXI, o mundo experimentou uma mudança de paradigma,
saindo de um estado de escassez de dados para um estado de superabundância de dados …