A survey on potentials, pathways and challenges of large language models in new-generation intelligent manufacturing
C Zhang, Q Xu, Y Yu, G Zhou, K Zeng, F Chang… - Robotics and Computer …, 2025 - Elsevier
Abstract Nowadays, Industry 5.0 starts to gain attention, which advocates that intelligent
manufacturing should adequately consider the roles and needs of humans. In this context …
manufacturing should adequately consider the roles and needs of humans. In this context …
Opportunities and Challenges in Transformer Neural Networks for Battery State Estimation: Charge, Health, Lifetime, and Safety
Battery technology plays a crucial role across various sectors, powering devices from
smartphones to electric vehicles and supporting grid-scale energy storage. To ensure their …
smartphones to electric vehicles and supporting grid-scale energy storage. To ensure their …
Serengeti: Massively multilingual language models for africa
Multilingual pretrained language models (mPLMs) acquire valuable, generalizable linguistic
information during pretraining and have advanced the state of the art on task-specific …
information during pretraining and have advanced the state of the art on task-specific …
Construction of an antidepressant priority list based on functional, environmental, and health risks using an interpretable mixup-transformer deep learning model
P Sun, H Liu, Y Zhao, N Hao, Z Deng… - Journal of Hazardous …, 2024 - Elsevier
As emerging pollutants, antidepressants (AD) must be urgently investigated for risk
identification and assessment. This study constructed a comprehensive-effect risk-priority …
identification and assessment. This study constructed a comprehensive-effect risk-priority …
Synthetic4Health: Generating Annotated Synthetic Clinical Letters
Since clinical letters contain sensitive information, clinical-related datasets can not be widely
applied in model training, medical research, and teaching. This work aims to generate …
applied in model training, medical research, and teaching. This work aims to generate …
[PDF][PDF] Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention
L Wang - arXiv preprint arXiv:2411.10156, 2024 - arxiv.org
To address the sycophancy problem caused by reinforcement learning from human
feedback in large language models, this research applies synthetic data intervention …
feedback in large language models, this research applies synthetic data intervention …
[HTML][HTML] Belt rotation in pipe conveyors: Development of an overlap monitoring system using digital twins, industrial Internet of things, and autoregressive language …
Belt rotation is a critical failure mode in pipe conveyors. However, overlap position
monitoring remains unexplored. Existing monitoring solutions are expensive and lack …
monitoring remains unexplored. Existing monitoring solutions are expensive and lack …
Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi
With the rise of online abuse, the NLP community has begun investigating the use of neural
architectures to generate counterspeech that can" counter" the vicious tone of such abusive …
architectures to generate counterspeech that can" counter" the vicious tone of such abusive …
A survey on cutting-edge relation extraction techniques based on language models
JA Diaz-Garcia, JAD Lopez - arXiv preprint arXiv:2411.18157, 2024 - arxiv.org
This comprehensive survey delves into the latest advancements in Relation Extraction (RE),
a pivotal task in natural language processing essential for applications across biomedical …
a pivotal task in natural language processing essential for applications across biomedical …
Towards Afrocentric natural language processing
I Adebara - 2024 - open.library.ubc.ca
This dissertation centers on Natural Language Processing (NLP) for African languages,
endeavoring to unravel the progress, challenges, and future prospects within this linguistic …
endeavoring to unravel the progress, challenges, and future prospects within this linguistic …