LLM-based embeddings for clustering and predicting integrated reporting quality levels of companies

Abstract

Artificial Intelligence (AI) offers various useful functions and algorithms that provide numerous benefits for firms to enhance their decision-making process. Moreover with the adoption of Integrated Reporting (IR) reporting practices which are critical communication channels for companies have become more practical. Given the importance of subjects it is believed that addressing LLM embeddings based AI methodologies will contribute positively to IR quality (IRQ) to achieve better results. Additionally grouping companies according to their IRQ characteristics will lead time and cost efficiency in decision-making. So that the main purpose of this study is to cluster companies with respect to their IRQ characteristics based on LLM embeddings and to use this grouping in further decision-making. This paper therefore provides significant evidence whether LLM is useful tool of AI techniques in IR practices and LLM-based clustering is an efficient way of generating predictions for decision-making. To do so the sample size of the study consists of 260 published IR in 2019. This study also introduces a novelty to the literature on the applicability of LLM with small data sets considering that the number of integrated reports published in a year is low or when the sample considered will be small. The findings reveal the superiority of LLM while indicating the usefulness of LLM in prediction of IRQ regarding different indicators of firms. Given the empirical evidence shown the techniques and steps should be adapted by firms both in identifying ways to improve IRQ and in different AI applications in the future. © 2025 Elsevier B.V. All rights reserved.