SDG Mapping Results for 1,000 Publications from Large Language Models: GPT-4o, Mixtral, Llama 2, Llama 3, Gemma 2, Qwen 2 and GPT-4o-mini

Randomly selected 1,000 publications from the Swinburne University of Technology research bank were used for SDG mapping tasks with the large language model GPT-4o and the open-source models Mixtral, Llama 2, Llama 3, Gemma 2, Qwen 2 and GPT-4o-mini. The input to each model consisted of the publication’s title and abstract. The designed prompt is as follows: PROMPT = '''Analyze the publication and determine the SDGs it aligns with. Evaluate against all the 17 SDGs provide the reason for alignment. In the end summarise the confidence levels(%) for each assigned SDG in JSON format. For example: {example}. Title: {title} Description: {description}''' example = '''{ 'Goal 6': 0.67, 'Goal 11': 0.50, 'Goal 3': 0.25}'''本研究从斯威本科技大学（Swinburne University of Technology）研究库中随机抽取1000篇学术文献，用于开展大语言模型的可持续发展目标（Sustainable Development Goals，SDGs）映射任务。参与测试的模型涵盖GPT-4o、开源模型Mixtral、Llama 2、Llama 3、Gemma 2、Qwen 2及GPT-4o-mini。 各模型的输入均为对应学术文献的标题与摘要。 本次实验设计的提示词如下： PROMPT = '''对该学术文献进行分析，确定其契合的可持续发展目标（SDGs）。对照全部17项可持续发展目标逐一开展评估，并说明契合理由。最终以JSON格式总结每个被分配SDG的置信度（百分比）。示例格式如下：{example}。标题：{title} 内容描述：{description}''' 示例格式为：{ 'Goal 6': 0.67, 'Goal 11': 0.50, 'Goal 3': 0.25}