all AI news
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
March 1, 2024, 5:49 a.m. | Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong Liu, Jing Shao
cs.CL updates on arXiv.org arxiv.org
Abstract: Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of pre-training, we pioneer the exploration of LLMs' trustworthiness during this period, focusing on five key dimensions: reliability, privacy, toxicity, fairness, and robustness. To begin with, we apply linear probing to LLMs. The high probing accuracy suggests that \textit{LLMs in early pre-training can …
arxiv cs.ai cs.cl dynamics language language models large language large language models pre-training tracing training type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Machine Learning Engineer - Sr. Consultant level
@ Visa | Bellevue, WA, United States