Dongwon Noh  Donghyeok Koh  Hyun Kim  D asol Kim  T aehoon Kim  Cheoneum Park

10.5626/JOK.2026.53.1.22

meeting summarization topic decomposition Chain-of-Thought Large Language Model

We propose a framework for summarizing meeting content based on specific topics using a large language model that combines extraction- and generation techniques. Each topic sencapsulates the central concept of the meeting, but its concise nature can complicate direct application during model inference. To overcome this challenge, we utilize a Chain-of-Thought (CoT) decomposition technique to interpret the topic and guide the extraction- and generation of summaries. Additionally, we employ an encoder with a long-context retriever to select meaningful sentences from extensive meeting content for topic summarization. Experimental results show that our extraction-generation framework achieves a ROUGE-1 score of 43.65, demonstrating its effectiveness in producing meeting summaries aligned with the specified topics.