Automatic Generation of Titles for Research Papers Using Language Models
2026-06-03 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors created a way to automatically make research paper titles from their abstracts using large language models. They tested their method on existing datasets and a new one they made from social science journals. They found that a model called PEGASUS-large, when fine-tuned, made better titles than other models like LLaMA-3 and GPT-3.5 used without extra training. The authors also showed that ChatGPT can create creative titles, and overall, AI-generated titles tend to be good and useful.
paper title generationlarge language modelsPEGASUS-largefine-tuningGPT-3.5-turbozero-shot learningabstract summarizationROUGEBERTScoreSciBERTScore
Authors
Tohida Rehman, Debarshi Kumar Sanyal, Samiran Chattopadhyay
Abstract
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.