Personalized Scientific Figure Caption Generation: An Empirical Study on Author-Specific Writing Style Transfer
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 3 of its 4 references that are in the map. First posted on arXiv 30 Sep 2025.
Builds on
3 of 4 references.
References · 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Personalized Image Generation from an Author Writing Style
- 2025Multi-LLM Collaborative Caption Generation in Scientific Documents
- 2023FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
- 2025Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SciCap Challenge 2023
- 2026Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer
- 2024A Survey on Personalized Content Synthesis with Diffusion Models
- 2024Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
- 2025RONA: Pragmatically Diverse Image Captioning with Coherence Relations