Large language models as semantic evaluators of embedded correlation substructures

Načítavam...
Obrázok miniatúry

Na stiahnutie

Dátum

2026

Názov časopisu

ISSN časopisu

Názov zväzku

Vydavateľ

Multidisciplinary Digital Publishing Institute : Basel

ISBN

ISSN

2673-9909

Abstrakt

Graphical methods of correlation analysis, such as correlation n-ptychs or hotspots, focus on the identification of the strength and direction of functional relationships between sets of attributes in multidimensional datasets. Since these correlation structures only take into account values of the attributes, situations arise when the relationship is coincidental, meaning that there is no real-world causality between the values of the observed attributes but these values still exhibit significant correlation. This problem of correlation analysis as a whole motivates the need for semantic evaluation of significant relationships identified using its methods—a task that could potentially be time- and resource-intensive when conducted manually. However, modern results in the large language model area provide tools for the automatization of such tasks. Hence, this work focuses on the design and implementation of a novel large language model-based method for semantic evaluation of correlation structures embedded in a correlation graph, specifically correlation n-ptychs for 𝑛∈{3, 4, 5} and correlation hotspots. In the method, the large language model is automatically prompted to assess the semantic nature of relationships in the set of correlation substructures of the dataset, identify their real-world relevance, and visualize the result in the form of a Semantic evaluation card. The proposed approach is evaluated using two benchmarking datasets focusing on the visualization method used in the model, large language model interaction with the correlation substructures, and comparative analysis with previously used tools in the area.

Popis

In: AppliedMath. Basel : Multidisciplinary Digital Publishing Institute, 2026. ISSN 2673-9909. Vol. 2026, no. 6 (6), pp. 1-20.

Kľúčové slová

korelačné štruktúry, correlation structures, veľké jazykové modely, large language models, vizualizácia, visualization

Výstup z projektu

APVV-24-0049 Digitalizácia a inteligentná obsahová analýza historických dokumentov pre odbornú archívnu činnosť a historickú vedu

Citácia

Práva a licenčné podmienky

CC BY Creative Commons Attribution 4.0 International
info:eu-repo/semantics/openAccess