@InProceedings{Deshpande2025_1261,
author = {Neha Deshpande and Stefan Hillmann and Sebastian Möller},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2025},
title = {Evaluating chain-of-thought prompting for abstractive dialogue summarization with large language models for German},
year = {2025},
editor = {Sven Grawunder},
month = mar,
pages = {265--272},
publisher = {TUDpress, Dresden},
abstract = {Dialogue summarization is a key NLP task for capturing conversational
nuances while conveying essential information. It has practical applications in
doctor-patient interactions, customer service, and multi-speaker meetings, enabling
effective review of discussions. However, the lack of dialogue summarization
datasets, especially in non-English languages, poses a challenge. This paper explores abstractive summarization using large English datasets, SAMSum and DialogSum, both translated into German. We compared 3-step Chain-of-Thought
(CoT) prompting with simple (1-step) prompting across four state-of-the-art Large
Language Models (LLMs). Model performance was evaluated using ROUGE
and BERTScore metrics. Our findings show CoT prompting outperforms simple
prompting for SAMSum for all models used, while further research is needed to
validate this approach for DialogSum.
},
isbn = {978-3-95908-803-9},
issn = {0940-6832},
keywords = {Poster},
url = {https://www.essv.de/pdf/2025_265_272.pdf},
}