Enhancing Large Language Models for Scientific Multimodal Summarization with Multimodal Output

Zusheng Tan, Xinyi Zhong, Jing-Yu Ji, Wei Jiang, Billy Chiu


Abstract
The increasing integration of multimedia such as videos and graphical abstracts in scientific publications necessitates advanced summarization techniques. This paper introduces Uni-SciSum, a framework for Scientific Multimodal Summarization with Multimodal Output (SMSMO), addressing the challenges of fusing heterogeneous data sources (e.g., text, images, video, audio) and outputting multimodal summary within a unified architecture. Uni-SciSum leverages the power of large language models (LLMs) and extends its capability to cross-modal understanding through BridgeNet, a query-based transformer that fuses diverse modalities into a fixed-length embedding. A two-stage training process, involving modal-to-modal pre-training and cross-modal instruction tuning, aligns different modalities with summaries and optimizes for multimodal summary generation. Experiments on two new SMSMO datasets show Uni-SciSum outperforms uni- and multi-modality methods, advancing LLM applications in the increasingly multimodal realm of scientific communication.
Anthology ID:
2025.coling-industry.22
Volume:
Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert, Kareem Darwish, Apoorv Agarwal
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
263–275
Language:
URL:
https://aclanthology.org/2025.coling-industry.22/
DOI:
Bibkey:
Cite (ACL):
Zusheng Tan, Xinyi Zhong, Jing-Yu Ji, Wei Jiang, and Billy Chiu. 2025. Enhancing Large Language Models for Scientific Multimodal Summarization with Multimodal Output. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 263–275, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Enhancing Large Language Models for Scientific Multimodal Summarization with Multimodal Output (Tan et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-industry.22.pdf