Leveraging Author-Specific Context for Scientific Figure Caption Generation: 3rd SciCap Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914082531049472 |
|---|---|
| author | Timklaypachara, Watcharapong Chiewhawan, Monrada Lekuthai, Nopporn Achakulvisut, Titipat |
| author_facet | Timklaypachara, Watcharapong Chiewhawan, Monrada Lekuthai, Nopporn Achakulvisut, Titipat |
| contents | Scientific figure captions require both accuracy and stylistic consistency to convey visual information. Here, we present a domain-specific caption generation system for the 3rd SciCap Challenge that integrates figure-related textual context with author-specific writing styles using the LaMP-Cap dataset. Our approach uses a two-stage pipeline: Stage 1 combines context filtering, category-specific prompt optimization via DSPy's MIPROv2 and SIMBA, and caption candidate selection; Stage 2 applies few-shot prompting with profile figures for stylistic refinement. Our experiments demonstrate that category-specific prompts outperform both zero-shot and general optimized approaches, improving ROUGE-1 recall by +8.3\% while limiting precision loss to -2.8\% and BLEU-4 reduction to -10.9\%. Profile-informed stylistic refinement yields 40--48\% gains in BLEU scores and 25--27\% in ROUGE. Overall, our system demonstrates that combining contextual understanding with author-specific stylistic adaptation can generate captions that are both scientifically accurate and stylistically faithful to the source paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07993 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Author-Specific Context for Scientific Figure Caption Generation: 3rd SciCap Challenge Timklaypachara, Watcharapong Chiewhawan, Monrada Lekuthai, Nopporn Achakulvisut, Titipat Computation and Language Artificial Intelligence Scientific figure captions require both accuracy and stylistic consistency to convey visual information. Here, we present a domain-specific caption generation system for the 3rd SciCap Challenge that integrates figure-related textual context with author-specific writing styles using the LaMP-Cap dataset. Our approach uses a two-stage pipeline: Stage 1 combines context filtering, category-specific prompt optimization via DSPy's MIPROv2 and SIMBA, and caption candidate selection; Stage 2 applies few-shot prompting with profile figures for stylistic refinement. Our experiments demonstrate that category-specific prompts outperform both zero-shot and general optimized approaches, improving ROUGE-1 recall by +8.3\% while limiting precision loss to -2.8\% and BLEU-4 reduction to -10.9\%. Profile-informed stylistic refinement yields 40--48\% gains in BLEU scores and 25--27\% in ROUGE. Overall, our system demonstrates that combining contextual understanding with author-specific stylistic adaptation can generate captions that are both scientifically accurate and stylistically faithful to the source paper. |
| title | Leveraging Author-Specific Context for Scientific Figure Caption Generation: 3rd SciCap Challenge |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.07993 |