FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback

Ashish Singh, Ashutosh Singh, Prateek Agarwal, Zixuan Huang, Arpita Singh, Tong Yu, Sungchul Kim, Victor Soares Bursztyn, Nesreen K. Ahmed, Puneet Mathur, Erik Learned-Miller, Franck Dernoncourt, Ryan Rossi


Abstract
Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness, leading to generated captions being misaligned with reader preferences. To address this issue, we introduce FigCaps-HF, a new framework for figure-caption generation that can incorporate domain expert feedback in generating captions optimized for reader preferences. Our framework comprises of 1) an automatic method for evaluating the quality of figure-caption pairs, and 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences. We demonstrate the effectiveness of our simple learning framework by improving performance over standard fine-tuning across different types of models. In particular, when using BLIP as the base model, our RLHF framework achieves a mean gain of 35.7%, 16.9%, 9%, and 11.4% in ROUGE, BLEU, Meteor, and CIDEr scores, respectively. Finally, we release a large-scale benchmark dataset with human feedback on figure-caption pairs to enable further evaluation and development of RLHF techniques for this problem.
Anthology ID:
2025.ranlp-1.135
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
1172–1182
Language:
URL:
https://aclanthology.org/2025.ranlp-1.135/
DOI:
Bibkey:
Cite (ACL):
Ashish Singh, Ashutosh Singh, Prateek Agarwal, Zixuan Huang, Arpita Singh, Tong Yu, Sungchul Kim, Victor Soares Bursztyn, Nesreen K. Ahmed, Puneet Mathur, Erik Learned-Miller, Franck Dernoncourt, and Ryan Rossi. 2025. FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1172–1182, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback (Singh et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.135.pdf