As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs). However, despite the advancements in edge computing, significant challenges remain in efficient training and deploying LLMs due to the computational demands and data privacy concerns associated with these models. This paper explores a collaborative training framework that integrates mobile users with edge servers to optimize resource allocation, thereby enhancing both performance and efficiency. Our approach leverages parameter-efficient fine-tuning (PEFT) methods, allowing mobile users to adjust the initial layers of the LLM while edge servers handle the more demanding latter layers. Specifically, we formulate a multi-objective optimization problem to minimize the total energy consumption and delay during training. We also address the common issue of instability in model performance by incorporating stability enhancements into our objective function. Through novel fractional programming technique, we achieve a stationary point for the formulated problem. Simulations demonstrate that our method reduces the energy consumption as well as the latency, and increases the reliability of LLMs across various mobile settings.

Artificial intelligence (AI) technology, combined with automatically collected big data hold the potential to solve many key clinical trial challenges. These include increasing trial efficiency through better protocol design, patient enrollment and retention, and study start-up, which were each named as prime candidates for improvement by nearly 40% of sponsors in a recent ICON-Pharma Intelligence survey.1 With clinical trials accounting for 40% of pharma research budgets2, sponsors need new ways to accelerate timelines and reduce costs. Data-driven protocols and strategies powered by advanced AI algorithms processing data automatically collected from mobile sensors and apps, electronic medical and administrative records, and other sources have the potential to significantly cut trial costs. They achieve this by improving data quality, increasing patient compliance and retention, and identifying treatment efficacy more efficiently and reliably than ever before.