@article{MEB7F5D28,
title = "LLM-based Extractive and Abstractive Korean Meeting Summarization with Topic Decomposition",
journal = "Journal of KIISE, JOK",
year = "2026",
issn = "2383-630X",
doi = "10.5626/JOK.2026.53.1.22",
author = "Dongwon Noh, Donghyeok Koh, Hyun Kim,D asol Kim,T aehoon Kim, Cheoneum Park",
keywords = "meeting summarization, topic decomposition, chain-of-thought, large language model",
abstract = "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."
}