Effectiveness of Explainable Artificial Intelligence (XAI) Techniques for Improving Human Trust in Machine Learning Models: A Systematic Literature Review
5
Issued Date
2025-01-01
Resource Type
eISSN
21693536
Scopus ID
2-s2.0-105007312700
Journal Title
IEEE Access
Rights Holder(s)
SCOPUS
Bibliographic Citation
IEEE Access (2025)
Suggested Citation
Wiratsin I.O., Ragkhitwetsagul C. Effectiveness of Explainable Artificial Intelligence (XAI) Techniques for Improving Human Trust in Machine Learning Models: A Systematic Literature Review. IEEE Access (2025). doi:10.1109/ACCESS.2025.3575022 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/110638
Title
Effectiveness of Explainable Artificial Intelligence (XAI) Techniques for Improving Human Trust in Machine Learning Models: A Systematic Literature Review
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Most decision-making processes worldwide are increasingly relying on artificial intelligence (AI) algorithms to enhance human welfare. Explainable Artificial Intelligence (XAI) techniques are pivotal in addressing the bottlenecks of utilizing machine learning (ML) algorithms, aiming to enhance human trust by providing transparency and interpretability. This paper conducts a systematic literature review to evaluate the effectiveness of various XAI techniques in improving human trust in ML models. In this paper, we perform a systematic literature review and our methodology involves a comprehensive search and analysis of relevant literature from 2015 to 2024, using well-known databases and adhering to PRISMA guidelines. The results indicate that XAI techniques significantly enhance user confidence by making ML models more transparent and understandable, facilitating error identification, and promoting better decision-making. However, gaps remain, including the need for standardized evaluation metrics, more user-centric evaluations, and studies on the long-term impact of XAI on user trust. Future research should focus on these areas to further improve the applicability and effectiveness of XAI techniques in diverse domains.