首页|Findings from University of Salerno Broaden Understanding of Intelligent Systems (Claude 2.0 large language model: Tackling a real-world classification problem with a new iterative prompt engineering approach)
Findings from University of Salerno Broaden Understanding of Intelligent Systems (Claude 2.0 large language model: Tackling a real-world classification problem with a new iterative prompt engineering approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on intelligent syste ms have been published. According to news originating from Salerno, Italy, by Ne wsRx editors, the research stated, "In the last year, Large Language Models (LLM s) have transformed the way of tackling problems, opening up new perspectives in various works and research fields, due to their ability to generate and underst and human languages." Our news reporters obtained a quote from the research from University of Salerno : "In this regard, the recent release of Claude 2.0 has contributed to the proce ssing of more complex prompts. In this scenario, the goal of this paper is to ev aluate the effectiveness of Claude 2.0 in a specific classification task. In par ticular, we considered the Forest cover-type problem, concerning the prediction of a cover-type value according to the geospatial characterization of target wor ldwide areas. To this end, we propose a novel iterative prompt template engineer ing approach, which integrates files by exploiting prompts and evaluates the qua lity of responses provided by the LLM. Moreover, we conducted several comparativ e analyses to evaluate the effectiveness of Claude 2.0 with respect to online an d batch learning models." According to the news editors, the research concluded: "The results demonstrated that, although some online and batch models performed better than Claude 2.0, t he new iterative prompt engineering approach improved the quality of responses, leading to better performance with increases ranging from 14% to 3 2 % in terms of accuracy, precision, recall, and F1-score."
University of SalernoSalernoItalyE uropeEngineeringIntelligent SystemsMachine Learning
NETL
NSTL
