多智能体协作提升关键词提取效果，适配长短文本差异。
MAPEX: A Multi-Agent Pipeline for Keyphrase Extraction
- 设计多智能体流程，分阶段协同完成关键词抽取
- 短文本用知识驱动，长文本用主题引导，动态适应长度
- 在6个数据集上平均超越当前最佳方法2.44%的F1@5得分
关键词提取是自然语言处理的基础任务。现有基于大模型的无监督提示方法通常采用单阶段推理流程，对所有文档使用统一提示，忽视了文档长度与模型结构的差异。这种‘一刀切’设计限制了大模型推理与生成能力的充分发挥，尤其在多样场景下表现受限。为此，我们提出MAPEX——首个将多智能体协作引入关键词提取的框架。MAPEX通过专家招募、候选提取、主题引导、知识增强和后处理等模块，协调基于大模型的智能体。采用双路径策略：短文本采用知识驱动提取，长文本则由主题引导。在三个不同大模型上的六个基准数据集上进行广泛实验，验证了其优异的泛化能力和普适性。MAPEX在F1@5指标上平均比最先进的无监督方法高出2.44%，比标准大模型基线高出4.01%。代码已开源：https://github.com/NKU-LITI/MAPEX。
原文摘要 · Abstract (English)
Keyphrase extraction is a fundamental task in natural language processing. However, existing unsupervised prompt-based methods for Large Language Models (LLMs) often rely on single-stage inference pipelines with uniform prompting, regardless of document length or LLM backbone. Such one-size-fits-all designs hinder the full exploitation of LLMs' reasoning and generation capabilities, especially given the complexity of keyphrase extraction across diverse scenarios. To address these challenges, we propose MAPEX, the first framework that introduces multi-agent collaboration into keyphrase extraction. MAPEX coordinates LLM-based agents through modules for expert recruitment, candidate extraction, topic guidance, knowledge augmentation, and post-processing. A dual-path strategy dynamically adapts to document length: knowledge-driven extraction for short texts and topic-guided extraction for long texts. Extensive experiments on six benchmark datasets across three different LLMs demonstrate its strong generalization and universality, outperforming the state-of-the-art unsupervised method by 2.44% and standard LLM baselines by 4.01% in F1@5 on average. Code is available at https://github.com/NKU-LITI/MAPEX.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。