作者位次 #3/5ACL 2026Poster· Natural Language Processing
M ega RAG : Multimodal Knowledge Graph-Based Retrieval Augmented Generation
Chi-Hsiang Hsiao · Yi-Cheng Wang · Tzung-Sheng Lin · Yi-Ren Yeh · Chu-song Chen
摘要
Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level conceptual understanding and holistic comprehension due to l...