From Data to Verified Model Knowledge: How Evidence Access Shapes Large Language Model Answers About Trained Machine-Learning Classifiers
Information · 19.11.2026 · 17 (11) · 1179
DOI: 10.3390/info17111179 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 19.11.2026. Verfasst von Attila Ficsor und 1 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research, Development and Innovation Office (NKFIH) of Hungary, Ministry for Culture and Innovation.
Abstract (Originalsprache)
Large language models (LLMs) are increasingly used to answer questions about predictive models, but a fluent answer about a model is not necessarily true of it. We propose a framework in which every answer is checked against a reference that independent software computes from the fitted model. The main finding is simple: the LLM was much more accurate when software had done the calculations than when it had to work them out from the model itself. In a confirmatory study with Gemini 2.5 Flash, the LLM correctly answered 16 of 36 questions whose answer follows exactly from the full model description, such as a prediction or a decision path, but 33 of the same 36 once software had computed the values from which the answer follows. A replication with 50 classifiers, five datasets and three LLM configurations, including a reasoning setting and an open-weight model, reproduced this pattern. Without model information, the LLMs declined to answer or guessed at chance level, and verified answers were reported faithfully once their origin was stated. Model-specific calculations should therefore be left to verified software, while the LLM reports and explains the checked results.
Förderung
- National Research, Development and Innovation Office (NKFIH) of Hungary
- Ministry for Culture and Innovation
Zitieren
APA
Ficsor, A., & Abonyi, J. (2026). From Data to Verified Model Knowledge: How Evidence Access Shapes Large Language Model Answers About Trained Machine-Learning Classifiers. Information, 17(11), 1179. https://doi.org/10.3390/info17111179
Vancouver
Ficsor A, Abonyi J. From Data to Verified Model Knowledge: How Evidence Access Shapes Large Language Model Answers About Trained Machine-Learning Classifiers. Information. 2026;17(11):1179. doi:10.3390/info17111179
BibTeX
@article{Ficsor2026,
author = {Ficsor, Attila and Abonyi, János},
title = {From Data to Verified Model Knowledge: How Evidence Access Shapes Large Language Model Answers About Trained Machine-Learning Classifiers},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1179},
doi = {10.3390/info17111179}
}
EUVIMED