CLAIJun 3

Automatic Generation of Titles for Research Papers Using Language Models

arXiv:2606.0508538.3
AI Analysis

This work addresses the challenge of title selection for researchers, but the gains are incremental as it applies existing methods to new datasets.

The authors propose a technique to automatically generate research paper titles from abstracts using language models, finding that fine-tuned PEGASUS-large outperforms other models across most evaluation metrics.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes