Enhancing Large Language Models for Scientific Multimodal Summarization with Multimodal Output

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.