Smooth it up!: Extractive summary coherence enhancement
Akhmetova D. Akhmetov I. Pak A. Gelbukh A.
February 2026SAGE Publications Ltd
Journal of Intelligent and Fuzzy Systems
2026#50Issue 2358 - 371 pp.
The paper focuses on the importance of coherence and preserving the breadth of content in summaries generated by the extractive text summarization method. The study utilized the dataset containing 16,772 pairs of extractive and corresponding abstractive summaries of scientific papers specifically tailored to increase text coherence. We smoothed the extractive summaries with a Large Language Model (LLM) fine-tuning approach and evaluated our results by applying the coefficient of variation approach. The statistical significance of the results was assessed using the Kolmogorov-Smirnov test and Z-test. We observed an increase in coherence in the predicted texts, highlighting the effectiveness of our proposed methods.
abstractive summary , Coherence , cohesion , extractive summary , GPT2 , random forest , seq2seq , summarization
Text of the article Перейти на текст статьи
Institute of Information and Computational Technologies, Almaty, Kazakhstan
Kazakh-British Technical University, Almaty, Kazakhstan
Instituto Politecnico Nacional, Mexico, Mexico
Institute of Information and Computational Technologies
Kazakh-British Technical University
Instituto Politecnico Nacional
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026