TY  - JOUR
T1  - LLM-based Extractive and Abstractive Korean Meeting Summarization with Topic Decomposition
AU  - Noh, Dongwon 
AU  - Koh, Donghyeok 
AU  - Kim, Hyun 
AU  - Kim, D asol 
AU  - Kim, T aehoon 
AU  - Park, Cheoneum 
JO  - Journal of KIISE, JOK
PY  - 2026
DA  - 2026/1/14
DO  - 10.5626/JOK.2026.53.1.22
KW  - meeting summarization
KW  - topic decomposition
KW  - chain-of-thought
KW  - large language model
AB  - 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.