Insight discovery in structured data

Kristyna Onderkova, a researcher presenting at the 1st Workshop for Young Researchers in Natural Language Generation (YNLG) in Hanoi, Vietnam, in October 2025, described her work on improving factual accuracy and depth in data-to-text generation by integrating large language models (LLMs) with symbolic operations through code generation. Her research investigates how implicit presuppositions in both models and humans affect generation outputs, evaluation, and the perceived interestingness of insights, aiming to leverage these presuppositions to improve insight generation from structured data.

Abstract My research focuses on improving textual inference in large language models LLMs for natural language generation, particularly in data-to-text generation. While LLMs are increasingly used to generate reports and insights from data, they often produce factually inaccurate or shallow outputs, limiting their usefulness. I work on integrating LLMs with symbolic operations through code generation for deeper and more faithful inferences. As generation tasks are often under-specified, both models and humans rely on implicit presuppositions, and mismatches can lead to errors or misinterpretation. I investigate how such presuppositions affect generation outputs and evaluation, how human presuppositions shape the perceived interestingness of the insights, and how they can be leveraged to improve insight generation.- Anthology ID: - 2025.ynlg-main.4 - Volume: Proceedings of the 1st Workshop for Young Researchers in Natural Language Generation /volumes/2025.ynlg-main/ - Month: - October - Year: - 2025 - Address: - Hanoi, Vietnam - Editors: Alyssa Allen /people/alyssa-allen/unverified/ , Nils Feldhus /people/nils-feldhus/ , Rudali Huidrom /people/rudali-huidrom/unverified/ , Michela Lorandi /people/michela-lorandi/ , Adarsa Sivaprasad /people/adarsa-sivaprasad/ , Patrícia Schmidtová /people/patricia-schmidtova/ - Venue: YNLG /venues/ynlg/ - SIG: SIGGEN /sigs/siggen/ - Publisher: - Association for Computational Linguistics - Note: - Pages: - 17–20 - Language: - URL: https://aclanthology.org/2025.ynlg-main.4/ https://aclanthology.org/2025.ynlg-main.4/ - DOI: - Cite ACL : - Kristyna Onderkova. 2025. Insight discovery in structured data https://aclanthology.org/2025.ynlg-main.4/ . In Proceedings of the 1st Workshop for Young Researchers in Natural Language Generation , pages 17–20, Hanoi, Vietnam. Association for Computational Linguistics. - Cite Informal : Insight discovery in structured data https://aclanthology.org/2025.ynlg-main.4/ Onderkova, YNLG 2025 - PDF: https://aclanthology.org/2025.ynlg-main.4.pdf https://aclanthology.org/2025.ynlg-main.4.pdf