用大模型自动生成论文标题，效果优于人工构思。
Automatic Generation of Titles for Research Papers Using Language Models
- 基于摘要用大模型生成标题，采用微调的PEGASUS-large模型
- 在多个数据集上表现最优，超越LLaMA-3和零样本GPT-3.5
- 适合科研人员快速构思标题，提升写作效率
论文标题需简洁传达核心思想与结论，但选题常具挑战性。本文提出一种基于开源预训练大模型的自动标题生成方法，利用CSPubSum、LREC-COLING-2024及新构建的SpringerSSAT（来自四本社会科学期刊）数据集进行训练与评估。采用GPT-3.5-turbo在零样本条件下生成标题，并以ROUGE、METEOR、MoverScore、BERTScore和SciBERTScore等指标衡量性能。实验表明，微调后的PEGASUS-large在多数指标上优于微调的LLaMA-3-8B及零样本GPT-3.5-turbo。进一步验证了ChatGPT生成创意标题的能力。整体而言，AI生成标题普遍恰当且可靠。
原文摘要 · Abstract (English)
The title of a research paper conveys its primary idea and, occasionally, its conclusions in a clear and concise manner. Choosing an appropriate title is often challenging, and automated title generation can assist authors in this task. In this work, we propose a technique to generate paper titles from abstracts using open-weight pre-trained and large language models. We use the CSPubSum and LREC-COLING-2024 datasets and introduce a new dataset, SpringerSSAT, curated from four Springer journals in the social sciences. Additionally, we use GPT-3.5-turbo in a zero-shot setting to generate titles. Model performance is evaluated with ROUGE, METEOR, MoverScore, BERTScore, and SciBERTScore metrics. Our experiments show that fine-tuned PEGASUS-large outperforms other models, including fine-tuned LLaMA-3-8B and zero-shot GPT-3.5-turbo, across most metrics. We further demonstrate that ChatGPT can generate creative paper titles. Overall, AI-generated titles are generally appropriate and reliable.
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。