Personalized Scientific Figure Caption Generation: An Empirical Study on Author-Specific Writing Style Transfer

2025/09/30 by Kim, Jaeyoung, Lee, Jongho, Choi, Hongjun +2
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2509.25817

openalex publication_date 2025/09/30 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

We study personalized figure caption generation using author profile data from scientific papers. Our experiments demonstrate that rich author profile data, combined with relevant metadata, can significantly improve the personalization performance of multimodal large language models. However, we also reveal a fundamental trade-off between matching author style and maintaining caption quality. Our findings offer valuable insights and future directions for developing practical caption automation systems that balance both objectives. This work was conducted as part of the 3rd SciCap challenge.

Citations

• Qwen2.5-VL Technical Report
• GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions
• Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization

Related

• Leveraging Author-Specific Context for Scientific Figure Caption Generation: 3rd SciCap Challenge
• LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles
• Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SciCap Challenge 2023
• Five Years of SciCap: What We Learned and Future Directions for Scientific Figure Captioning
• SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning