Query-focused tabular summarization is an emerging task in table-to-text generation that synthesizes a summary response from tabular data based on user queries. Traditional transformer-based approaches face challenges due to token limitations and the complexity of reasoning over large tables. To address these challenges, we introduce DETQUS (Decomposition-Enhanced Transformers for QUery-focused Summarization), a system designed to improve summarization accuracy by leveraging tabular decomposition alongside a fine-tuned encoder-decoder model. DETQUS employs a large language model to selectively reduce table size, retaining only query-relevant columns while preserving essential information. This strategy enables more efficient processing of large tables and enhances summary quality. Our approach, equipped with table-based QA model Omnitab, achieves a ROUGE-L score of 0.4437, outperforming the previous state-of-the-art REFACTOR model (ROUGE-L: 0.422). These results highlight DETQUS as a scalable and effective solution for query-focused tabular summarization, offering a structured alternative to more complex architectures.
View on arXiv@article{khan2025_2503.05935,
title={ DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization },
author={ Yasir Khan and Xinlei Wu and Sangpil Youm and Justin Ho and Aryaan Shaikh and Jairo Garciga and Rohan Sharma and Bonnie J. Dorr },
journal={arXiv preprint arXiv:2503.05935},
year={ 2025 }
}