Porting an LLM based Application from ChatGPT to an On-Premise Environment
This program is tentative and subject to change.
Given the data-intensive nature of Machine Learning (ML) systems in general, and Large Language Models (LLM) in particular, using them in cloud based environments can become a challenge due to legislation related to privacy and security of data. Taking such aspects into consideration implies porting the LLMs to an on-premise environment, where privacy and security can be controlled. In this paper, we study this porting process of a real-life application using ChatGPT, which runs in a public cloud, to an on-premise environment. The application being ported is ACME, a system that leverages Large Language Models (LLMs) and sophisticated data analytics to enhance the assessment of procurement call bids. The main considerations in the porting process include transparency of open source models and cost of hardware, which are central design choices of the on-premise environment. In addition to presenting the porting process, we evaluate downsides and benefits associated with porting.
This program is tentative and subject to change.
Sun 27 AprDisplayed time zone: Eastern Time (US & Canada) change
16:00 - 17:30 | |||
16:00 30mPaper | DockInsight: A Knowledge-Augmented Dependency Extraction Approach for Dockerfile ICSR Zhu Zhiling Zhejiang University of Technology, Tieming Chen Zhejiang University of Technology, Yunjin Zhong Zhejiang University of Technology, Qijie Song Zhejiang University of Technology | ||
16:30 15mPaper | Porting an LLM based Application from ChatGPT to an On-Premise Environment ICSR Teemu Paloniemi University of Jyväskylä, Manu Setälä Solita Oy, Tommi Mikkonen University of Jyvaskyla | ||
16:45 30mPaper | Predicting the Root Cause of Flaky Tests Based on Test Smells ICSR Jing Wang College of Information Science and Technology, Beijing University of Chemical Technology, Weixi Zhang College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing, China, Weixi Zhang College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing, China, Ruilian Zhao Beijing University of Chemical Technology, Ying Shang Beijing University of Chemical Technology | ||
17:15 15mPaper | Towards Patterns for a Reference Assurance Case for Autonomous Inspection Robots ICSR Dhaminda B. Abeywickrama Department of Computer Science, The University of Manchester, UK, Michael Fisher University of Manchester, UK, Frederic Wheeler Regulatory Support Directorate, Amentum, Louise Dennis The University of Manchester | ||