DNB-AI-Project at SemEval-2025 Task 5：用于自动化主题标引的LLM集成方法
DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing
AI总结：
本文提出用于自动化主题标引的LLM集成系统，结合少样本提示与后处理步骤进行关键词映射、集成投票和相关性排名，在SemEval-2025 Task 5定性评估中获最佳成绩。
摘要：
本文介绍了我们为SemEval-2025 Task 5：LLMs4Subjects：基于LLM的国家技术图书馆开放获取目录自动化主题标签系统开发的系统。我们的系统依赖于向选定的LLM提供带有智力标注记录的不同示例进行提示，并要求LLM类似地为新记录建议关键词。这种少样本提示技术与一系列后处理步骤相结合，这些步骤将生成的关键词映射到目标词汇表，将生成的主题术语聚合为集成投票，最后根据它们与记录的相关性进行排名。我们的系统在所有主题轨道的定量排名中排名第四，但在主题标引专家进行的定性排名中取得了最佳结果。
英文摘要：
This paper presents our system developed for the SemEval-2025 Task 5: LLMs4Subjects: LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog. Our system relies on prompting a selection of LLMs with varying examples of intellectually annotated records and asking the LLMs to similarly suggest keywords for new records. This few-shot prompting technique is combined with a series of post-processing steps that map the generated keywords to the target vocabulary, aggregate the resulting subject terms to an ensemble vote and, finally, rank them as to their relevance to the record. Our system is fourth in the quantitative ranking in the all-subjects track, but achieves the best result in the qualitative ranking conducted by subject indexing experts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
