In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.
Department of Statistics and Operations Research, UNC-Chapel Hill(统计与运筹学系,北卡罗来纳大学 Chapel Hill 分校);Imperial College Business School, Imperial College London(帝国理工学院伦敦校区商学院)
Prompt-based Personality Profiling: Reinforcement Learning for Relevance Filtering
Institut für Maschinelle Sprachverarbeitung, University of Stuttgart, Germany(机械语言处理研究所,斯图加特大学);Computational Digital Psychology, Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart, Germany(计算数字心理学,智能系统反思交流论坛,斯图加特大学);Fundamentals of Natural Language Processing, University of Bamberg, Germany(自然语言处理基础,巴姆堡大学)
Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(一般人工智能国家重点实验室,智能科学与技术学院,北京大学)
On the Performance of LLMs for Real Estate Appraisal
LIRIS, KU Leuven, Leuven, Belgium(LIRIS,KU莱顿,比利时);Department of Business Informatics and Operations Management, Ghent University, Ghent, Belgium(商业信息学与运营管理系,根特大学,比利时);Department of Decision Analytics and Risk, University of Southampton, Southampton, UK(决策分析与风险系,南安普顿大学,英国)
Forecasting Future Language: Context Design for Mention Markets
LinqAlpha;Massachusetts Institute of Technology(麻省理工学院);Kalshi;IBM;LG AI Research(LG AI研究);University of Florida(佛罗里达大学);Seoul National University(首尔国立大学);Pusan National University(釜山国立大学);University of California, Berkeley(加州大学伯克利分校);UNIST(全南国立大学)