Measuring Social Norms of Large Language Models
We present a new challenge to examine whether large language models understand social
norms. In contrast to existing datasets, our dataset requires a fundamental understanding of …
norms. In contrast to existing datasets, our dataset requires a fundamental understanding of …
[PDF][PDF] A Comparative Survey: Reusing Small Pre-Trained Models for Efficient Large Model Training
D Pandey, J Ghebremichael, Z Qi… - Proc. of Workshops of …, 2024 - tongshu83.github.io
Training large language models is becoming increasingly complex due to the rapid
expansion in their size, resulting in significant computational costs. To address this …
expansion in their size, resulting in significant computational costs. To address this …
[HTML][HTML] Balancing Privacy and Robustness in Prompt Learning for Large Language Models
C Shi, J Su, C Chu, B Wang, D Feng - Mathematics, 2024 - mdpi.com
This paper tackles the critical issue of privacy in Natural Language Processing (NLP)
systems that process sensitive data by introducing a novel framework combining differential …
systems that process sensitive data by introducing a novel framework combining differential …
A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
Retrieval-augmented generation (RAG) is a framework enabling large language models
(LLMs) to enhance their accuracy and reduce hallucinations by integrating external …
(LLMs) to enhance their accuracy and reduce hallucinations by integrating external …
AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
In recent years, with the rapid application of large language models across various fields,
the scale of these models has gradually increased, and the resources required for their pre …
the scale of these models has gradually increased, and the resources required for their pre …