CoChat
Sign Up
Cited by 168Explainable Artificial Intelligence (XAI)Software Testing and Debugging TechniquesEthics and Social Impacts of AI

Recent Emerging Techniques in Explainable Artificial Intelligence to Enhance the Interpretable and Understanding of AI Models for Human

Open access
Mathew, Daniel Enemona, Ebem, Deborah Uzoamaka, Ikegwu, Anayo Chukwu, Ukeoma, Pamela Eberechukwu, Dibiaezue, Ngozi Fidelia·2025·Neural Processing Letters
DOI 10.1007/s11063-025-11732-2
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent advancements in Explainable Artificial Intelligence (XAI) aim to bridge the gap between complex artificial intelligence (AI) models and human understanding, fostering trust and usability in AI systems. However, challenges persist in comprehensively interpreting these models, hindering their widespread adoption. This study addresses these challenges by exploring recently emerging techniques in XAI. The primary problem addressed is the lack of transparency and interpretability in AI models to humanity for institution-wide use, which undermines user trust and inhibits their integration into critical decision-making processes. Through an in-depth review, this study identifies the objectives of enhancing the interpretability of AI models and improving human understanding of their decision-making processes. Various methodological approaches, including post-hoc explanations, model transparency methods, and interactive visualization techniques, are investigated to elucidate AI model behaviours. We further present techniques and methods to make AI models more interpretable and understandable to humans including their strengths and weaknesses to demonstrate promising advancements in model interpretability, facilitating better comprehension of complex AI systems by humans. In addition, we provide the application of XAI in local use cases. Challenges, solutions, and open research directions were highlighted to clarify these compelling XAI utilization challenges. The implications of this research are profound, as enhanced interpretability fosters trust in AI systems across diverse applications, from healthcare to finance. By empowering users to understand and scrutinize AI decisions, these techniques pave the way for more responsible and accountable AI deployment.

AI snapshot

Written from the paper’s full text.

TL;DR

This narrative review surveys recent Explainable AI (XAI) techniques — post-hoc explanations, model transparency methods, and interactive visualization — and argues they are needed to make complex AI models interpretable and trustworthy for human users. It catalogs techniques, AI component strengths/weaknesses, and domain-specific applications (healthcare, finance, retail, agriculture, education, transport, legal), then lists challenges and open research directions.

Key findings

  • Explanatory depth in XAI is achieved through feature importance, visualization, counterfactual explanations, and local-vs-global explanations; post-hoc methods such as SHAP and LIME are presented as the main tools for explaining otherwise opaque models (deep neural networks, ensembles) across healthcare, finance, agriculture, education, retail, and transport.
  • The paper reports that XAI faces a persistent trade-off between model complexity and interpretability, lacks commonly accepted interpretability standards, and struggles with context-aware explanations tailored to different user groups.
  • Cited evidence on labor-market demand: analysis of 279.87 million US internet job posts between 2010 and 2022 found demand for statistical talent with AI expertise increased 31 times, yielding 932 AI-related employment categories.
  • Cited evidence on finance: banking loan acceptance rates dropped to 61–70% and further to 50% post-pandemic, with applicants often unaware of rejection reasons; an XAI framework using Random Forest with LIME and SHAP explainers is described as improving loan-acceptance prediction transparency and accuracy.

Methods

  • Design: a literature review / survey of emerging XAI techniques, organized into explanatory depth, techniques for interpretability, understandability of AI components, local use cases, challenges and solutions, and open research directions.
  • Data: no datasets were generated or analyzed ("No datasets were generated or analysed during the current study"); the work synthesizes prior studies, with illustrative tables of techniques (e.g., Sensitivity Analysis, Rule-Based Models) and of local use cases with challenges and solutions.
  • Analysis: narrative synthesis with supporting citations; no systematic review protocol, meta-analysis, or empirical evaluation is described.

Limitations

  • The paper states no explicit limitations section; it reports no funding, no datasets, and no code.
  • Evident from the text: it is a narrative review without a stated systematic search strategy, inclusion criteria, or quantitative synthesis, so coverage and selection of cited works are not verifiable.
  • Evident from the text: several tables are truncated or garbled in the provided version (e.g., Table 1 and Table 3 rows are partially cut off), and the paper's own contributions are descriptive rather than empirically validated.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1007/s11063-025-11732-2

Cites

Statistics

Nothing to recompute.

Claims the paper makes

0 of 27 cited sources checked · 0 supported · 0 flagged

  • Premisecitation

    XAI provides a breakdown of credit scores, offering transparency into how individual scores are calculated and the factors influencing them.

    “Talaat et al. [146] showed that XAI also provides a breakdown of credit scores, offering transparency into how individual scores are calculated and the factors influencing them.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [146] source

      Not checked in the free run.

  • Premisecitation

    Visualization techniques play a crucial role in achieving explanatory depth by providing intuitive representations of AI model behaviour.

    “Visualization techniques play a crucial role in achieving explanatory depth by providing intuitive representations of AI model behaviour by transforming complex model outputs into visually interpretable formats, such as charts, graphs, or heatmaps, users can better understand the patterns and relationships captured by the AI system Minh et al. [105].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [105] source

      Not checked in the free run.

  • Interpretationnone given

    None of the existing studies provides a comprehensive approach in solving the inherent issues beclouding the deployment of AI.

    “However, to our knowledge, none of these studies provides a comprehensive approach in solving the inherent issues beclouding the deployment of AI.”
    Quote in the paperNot a substantial claim
  • Premisecitation

    Counterfactual explanations offer another avenue for achieving explanatory depth in XAI by providing insights into 'what-if' scenarios.

    “In the work of Stepin et al. [141] counterfactual explanations offer another avenue for achieving explanatory depth in XAI by providing insights into”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [141] source

      Not checked in the free run.

  • Interpretationreasoning

    XAI techniques, including feature importance, visualization, and counterfactual explanations, enhance explanatory depth by enabling users to comprehend and trust the decisions made by AI systems.

    “Therefore, XAI techniques, including feature importance, visualization, and counterfactual explanations, enhance explanatory depth by enabling users to comprehend and trust the decisions made by AI systems.”
    Quote in the paperSubstantial claim
  • Classified as probably not a substantial claim. 46
  • May combine two claims. 42

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisenone given

    SHAP helps identify how patient features (such as age, symptoms, or lab results) influence a diagnosis or treatment recommendation, building trust in AI-driven decisions.

    “Some of the post-hoc explanations include in healthcare, SHAP helps identify how patient features (such as age, symptoms, or lab results) influence a diagnosis or treatment recommendation, building trust in AI-driven decisions.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Premisereasoning

    Trust is built through transparent processes, reliable outcomes, and ethical considerations.

    “Trust is built through transparent processes, reliable outcomes, and ethical considerations.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Transparency ensures that the internal mechanisms of AI models are clear and understandable, thereby promoting trust and accountability.

    “Transparency ensures that the internal mechanisms of AI models are clear and understandable, thereby promoting trust and accountability.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    XAI identifies key risk factors associated with credit decisions, aiding in the identification and mitigation of potential risks.

    “Heng and Subramanian [62] presented that XAI further identifies key risk factors associated with credit decisions, aiding in the identification and mitigation of potential risks.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [62] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    XAI plays a crucial role in disease diagnosis, as AI models used in medical diagnosis can explain their decisions, helping doctors understand the reasoning behind a diagnosis.

    “Explainable Artificial Intelligence (XAI) plays a crucial role in disease diagnosis, AI models used in medical diagnosis can explain their decisions, helping doctors understand the reasoning behind a diagnosis.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    LIME explains individual predictions, clarifying why specific diagnoses or risk scores were assigned, which is especially useful for case-specific interpretations.

    “LIME, on the other hand, explains individual predictions, clarifying why specific diagnoses or risk scores were assigned, which is especially useful for case-specific interpretations.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning

    By empowering users to understand and scrutinize AI decisions, XAI techniques pave the way for more responsible and accountable AI deployment.

    “By empowering users to understand and scrutinize AI decisions, these techniques pave the way for more responsible and accountable AI deployment.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    In finance, SHAP clarifies how factors like credit history, income, and debt impact loan approvals or risk assessments, supporting regulatory compliance and customer trust.

    “In finance, SHAP clarifies how factors like credit history, income, and debt impact loan approvals or risk assessments, supporting regulatory compliance and customer trust.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationcitation

    Ensuring explainability in AI for disease diagnosis is crucial for fostering trust, transparency, and acceptance of AI-based diagnostic systems within the healthcare sector.

    “Ensuring explainability in AI for disease diagnosis is crucial for fostering trust, transparency, and acceptance of AI-based diagnostic systems within the healthcare sector.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    AI-generated explanations can inadvertently lead to negative consequences and potentially harmful manipulation of trust.

    “These findings, which have significant implications for XAI, reveal that AI-generated explanations can inadvertently lead to negative consequences and potentially harmful manipulation of trust.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [39] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    Enhanced interpretability fosters trust in AI systems across diverse applications, from healthcare to finance.

    “The implications of this research are profound, as enhanced interpretability fosters trust in AI systems across diverse applications, from healthcare to finance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    In retail, SHAP highlights key customer features, like purchase history and demographics, that influence behavior predictions, aiding in personalization strategies.

    “In retail, SHAP highlights key customer features, like purchase history and demographics, that influence behavior predictions, aiding in personalization strategies.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Privacy concerns involve safeguarding sensitive information and ensuring responsible data handling practices.

    “Privacy concerns involve safeguarding sensitive information and ensuring responsible data handling practices.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Interpretationcitation

    AI practitioners can employ certain techniques and methods to enhance model interpretability and understandability, fostering responsible AI deployment and increasing user trust.

    “AI practitioners can employ certain techniques and methods to enhance model interpretability and understandability, fostering responsible AI deployment and increasing user trust.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationreasoning

    This review emphasizes the necessity of explainability in digital pathology to prevent mistakes and ensure patient safety, introducing various explainable AI techniques that enhance the transparency of these algorithms.

    “This review emphasizes the necessity of explainability in digital pathology to prevent mistakes and ensure patient safety, introducing various explainable AI techniques that enhance the transparency of these algorithms.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

    Premisenone given

    Causality aims to uncover the cause-and-effect relationships within AI decisions, providing deeper insights into model behaviour.

    “Causality aims to uncover the cause-and-effect relationships within AI decisions, providing deeper insights into model behaviour.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Premisenone given

    Post-hoc methods are beneficial for explaining complex models that are not naturally interpretable, such as deep neural networks or ensemble models.

    “Post-hoc methods are beneficial for explaining complex models that are not naturally interpretable, such as deep neural networks or ensemble models.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    By harnessing AI capabilities, AI systems enhance human intelligence, automate repetitive tasks, and tackle complex challenges across diverse fields.

    “By harnessing these capabilities, AI systems enhance human intelligence, automate repetitive tasks, and tackle complex challenges across diverse fields.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Explainability in AI for credit scoring and risk assessment helps lenders make responsible lending decisions and empowers borrowers to understand and improve their financial profiles.

    “Explainability in AI for credit scoring and risk assessment helps lenders make responsible lending decisions and empowers borrowers to understand and improve their financial profiles [62].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [62] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    In education, SHAP clarifies how factors like attendance, grades, and engagement affect predictions of student performance or dropout risk, helping educators target areas for intervention.

    “In education, SHAP clarifies how factors like attendance, grades, and engagement affect predictions of student performance or dropout risk, helping educators target areas for intervention.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    XAI ensures regulatory compliance by providing explanations and justifications for credit decisions, helping financial institutions adhere to regulatory requirements and ethical standards while making informed lending decisions.

    “XAI ensures regulatory compliance by providing explanations and justifications for credit decisions, helping financial institutions adhere to regulatory requirements and ethical standards while making informed lending decisions.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [48] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisenone given

    In agriculture, SHAP explains predictions on crop yield, disease risk, and soil quality by highlighting the impact of factors like weather, soil pH, and fertilizer use, supporting data-driven crop management.

    “In agriculture, SHAP explains predictions on crop yield, disease risk, and soil quality by highlighting the impact of factors like weather, soil pH, and fertilizer use, supporting data-driven crop management while LIME offers specific explanations for cases such as high disease risk scores, guiding targeted interventions.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The primary objective of Explainable Artificial Intelligence (XAI) is to improve the comprehension and acceptance of AI systems.

    “Figure 1 illustrates that the primary objective of Explainable Artificial Intelligence (XAI) is to improve the comprehension and acceptance of AI systems.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    XAI is instrumental in credit scoring and risk assessment within the finance sector, operating across several key dimensions like identifying feature importance, and allowing financial institutions to understand the factors driving creditworthiness and risk.

    “Matcov [103] explained that XAI is instrumental in credit scoring and risk assessment within the finance sector, operating across several key dimensions like identifying feature importance, and allowing financial institutions to understand the factors driving creditworthiness and risk.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [103]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    In transport, SHAP identifies factors affecting delivery times, maintenance needs, or fuel efficiency-such as traffic, vehicle age, or route length-helping to boost efficiency.

    “In transport, SHAP identifies factors affecting delivery times, maintenance needs, or fuel efficiency-such as traffic, vehicle age, or route length-helping to boost efficiency.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    XAI enhances model interpretability, allowing healthcare providers to understand how a diagnostic model arrives at its conclusions.

    “Moreover, XAI enhances model interpretability, allowing healthcare providers to understand how a diagnostic model arrives at its conclusions.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    The study by Del Ser et al. demonstrates across six classification tasks using image and 3D data evidence of trade-offs between objectives and consistency of the generated explanations with human understanding, and the framework's ability to reveal concept-based biases and misrepresented attributes within the model's input domain.

    “The study demonstrates across six classification tasks using image and 3D data confirm evidence of trade-offs between objectives and consistency of the generated explanations with human understanding, and the framework's ability to reveal concept-based biases and misrepresented attributes within the model's input domain.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [34] source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    XAI enhances transparency, accountability, and effectiveness in credit scoring and risk assessment processes, enabling financial institutions to make more accurate and fair credit decisions while ensuring regulatory compliance.

    “Overall, XAI enhances transparency, accountability, and effectiveness in credit scoring and risk assessment processes, enabling financial institutions to make more accurate and fair credit decisions while ensuring regulatory compliance.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Feature importance technique seeks to improve explanatory depth by pinpointing the most significant features influencing an AI model's decisions.

    “Zacharias et al. [169] explained that the feature importance technique seeks to improve explanatory depth by pinpointing the most significant features influencing an AI model's decisions.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [169] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

    Premisenone given

    Usability emphasizes making AI systems accessible and user-friendly, catering to diverse stakeholders.

    “Usability emphasizes making AI systems accessible and user-friendly, catering to diverse stakeholders.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The primary objective of XAI is achieved by integrating essential principles such as transparency, reliability, causality, usability, privacy, trust, and fairness.

    “This is achieved by integrating essential principles such as transparency, reliability, causality, usability, privacy, trust, and fairness.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Fairness addresses the need for unbiased and equitable AI decisions, mitigating the impact of algorithmic biases, and thereby promoting ethical and responsible AI practices across various domains.

    “Fairness addresses the need for unbiased and equitable AI decisions, mitigating the impact of algorithmic biases, and thereby promoting ethical and responsible AI practices across various domains.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

    Premisenone given

    Reliability focuses on consistently producing accurate and dependable results, contributing to the overall credibility of AI systems.

    “Reliability focuses on consistently producing accurate and dependable results, contributing to the overall credibility of AI systems.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    The study emphasizes the importance of collaboration between computer scientists, ethicists, psychologists, sociologists, and other disciplines, highlighting the need for a holistic approach to address the multifaceted challenges of XAI effectively.

    “Furthermore, the study emphasizes the importance of collaboration between computer scientists, ethicists, psychologists, sociologists, and other disciplines, highlighting the need for a holistic approach to address the multifaceted challenges of XAI effectively.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    The deployment of XAI accounts for the experience and authority of farmers, and comprehension increases farmers' trust in AI systems and makes them more effective.

    “The deployment of XAI accounts for the experience and authority of the farmers and comprehension increases the farmer's trust in AI systems and makes them more effective [64].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [64] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Protecting taxpayers' rights requires the implementation of XAI technologies, which can make the operations and decisions of tax-related AI systems comprehensible to taxpayers, administrative appeal bodies, and the courts.

    “Kuźniacki et al. [84] article contends that protecting taxpayers' rights requires the implementation of XAI technologies, which can make the operations and decisions of tax-related AI systems comprehensible to taxpayers, administrative appeal bodies, and the courts.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [84] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    Trustworthy AI is needed to enable healthcare professionals to make informed, accountable decisions, which makes explainable AI essential.

    “Trustworthy AI is needed to enable healthcare professionals to make informed, accountable decisions, which makes explainable AI essential.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationnone given

    XAI plays a crucial role in reinstating the contestability of decisions made by autonomous driving systems, potentially safeguarding users from undue harm and establishing a basis for legal recourse.

    “XAI plays a crucial role in reinstating the contestability of decisions made by autonomous driving systems, potentially safeguarding users from undue harm and establishing a basis for legal recourse.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    Explainable AI enhances the speed and accuracy of decision-making processes by elucidating the rationale behind individual recommendations or decisions, complementing consumers' interactions with AI systems.

    “By elucidating the rationale behind individual recommendations or decisions, explainable AI enhances the speed and accuracy of decision-making processes by complementing consumers' interactions with AI systems.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    Recent advancements in XAI represent a crucial step toward bridging the gap between complex AI models and human understanding.

    “The recent advancements in Explainable Artificial Intelligence (XAI) represent a crucial step toward bridging the gap between complex AI models and human understanding.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationcitation

    Explainability in agriculture supports sustainable farming practices, optimal resource utilization, and resilient crop management.

    “Explainability in agriculture supports sustainable farming practices, optimal resource utilization, and resilient crop management.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Interpretationcitation

    In local use cases, ensuring explainability presents unique challenges and opportunities.

    “In local use cases, where AI is applied within specific contexts such as healthcare, finance, retail, agriculture, education, transport, and logistics, ensuring explainability presents unique challenges and opportunities.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Premisecitation

    Current advancements in XAI do not adequately meet legal requirements, particularly concerning the correctness (or fidelity) and confidence estimates of XAI methods.

    “It highlights that the current advancements in XAI do not adequately meet these legal requirements, particularly concerning the correctness (or fidelity) and confidence estimates of XAI methods.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [47] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    An XAI framework integrated with Random Forest algorithms offers clear explanations for loan decisions, enhancing transparency in the lending process.

    “Nallakaruppan et al. [110] proposed an XAI framework integrated with Random Forest algorithms, offering clear explanations for loan decisions, thus enhancing transparency in the lending process.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [110] source

      Not checked in the free run.

  • May combine two claims.

    Interpretationcitation

    In assessment and grading, XAI enhances objectivity and fairness by providing transparent insights into grading criteria and performance metrics, enabling educators to make informed evaluations and provide constructive feedback.

    “In assessment and grading, XAI enhances objectivity and fairness by providing transparent insights into grading criteria and performance metrics, enabling educators to make informed evaluations and provide constructive feedback [67,69].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [67] source

      Not checked in the free run.

    • cites [69] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    By enhancing transparency, XAI fosters accountability, supports audits, and helps organizations meet compliance obligations, such as the GDPR in the EU, which mandates the right to explanations for automated decisions.

    “By enhancing transparency, XAI fosters accountability, supports audits, and helps organizations meet compliance obligations, such as the GDPR in the EU, which mandates the right to explanations for automated decisions.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    XAI empowers farmers with actionable insights and decision support tools to optimize crop productivity, improve resilience against environmental challenges, and enhance sustainability in agriculture practices.

    “Overall, XAI empowers farmers with actionable insights and decision support tools to optimize crop productivity, improve resilience against environmental challenges, and enhance sustainability in agriculture practices.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    Implementation of XAI in local use cases has great potential to improve decision-making processes in various fields such as healthcare, finance, and law.

    “Furthermore, the implementation of XAI in local use cases has great potential to improve decision-making processes in various fields such as healthcare, finance, and law.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    An XAI framework using LIME and SHAP explainers provides local and global insights on various parameters, significantly improving the accuracy and reliability of loan acceptance predictions.

    “This XAI framework utilizes LIME and SHAP explainers to provide local and global insights on various parameters, significantly improving the accuracy and reliability of loan acceptance predictions.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [110] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    XAI has the potential to revolutionize the way students perceive, absorb, and comprehend course materials, facilitating enhanced knowledge transfer and optimization of classroom learning experiences.

    “XAI has the potential to revolutionize the way students perceive, absorb, and comprehend course materials, facilitating enhanced knowledge transfer and optimization of classroom learning experiences.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    Lack of explainability and trust currently limits the full utilization of AI systems.

    “However, the lack of explainability and trust currently limits the full utilization of AI systems.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    By improving explanatory depth, XAI techniques provide users with insights into AI decision-making processes, thereby enhancing transparency and trust.

    “By improving explanatory depth, XAI techniques provide users with insights into AI decisionmaking processes, thereby enhancing transparency and trust.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    XAI helps mitigate the environmental impact of transportation by optimizing route planning, load distribution, and vehicle utilization to minimize emissions and carbon footprint.

    “Furthermore, XAI helps mitigate the environmental impact of transportation by optimizing route planning, load distribution, and vehicle utilization to minimize emissions and carbon footprint, promoting sustainable and eco-friendly practices in the transportation and logistics industry (T. [18,95]).”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [18] source

      Not checked in the free run.

    • cites [95] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationnone given

    XAI enhances demand forecasting accuracy by analyzing market trends, customer behaviour, and historical data to predict future demand, enabling companies to optimize inventory management and resource allocation.

    “XAI enhances demand forecasting accuracy by analyzing market trends, customer behaviour, and historical data to predict future demand, enabling companies to optimize inventory management and resource allocation.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    Enhanced transparency provided by XAI has the potential to enable traceability, leading to a more precise evaluation of due diligence and liability in the event of accidents, thereby benefiting insurance companies and regulatory bodies.

    “The enhanced transparency provided by XAI has the potential to enable traceability, leading to a more precise evaluation of due diligence and liability in the event of accidents, thereby benefiting insurance companies and regulatory bodies.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    Implementing emerging techniques in XAI can foster trust and acceptance among users, as they gain a deeper understanding of AI model behaviour and reasoning, leading to increased confidence in the technology.

    “Also, implementing emerging techniques in XAI can foster trust and acceptance among users, as they gain a deeper understanding of AI model behaviour and reasoning, leading to increased confidence in the technology.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    XAI empowers transportation and logistics companies with transparent insights and data-driven solutions to optimize operations, improve efficiency, and reduce environmental impact across the supply chain.

    “Overall, XAI empowers transportation and logistics companies with transparent insights and data-driven solutions to optimize operations, improve efficiency, and reduce environmental impact across the supply chain.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    XAI enhances weather forecasting accuracy by integrating complex weather data with historical patterns, allowing farmers to anticipate and mitigate the impact of adverse weather conditions on crops.

    “XAI enhances weather forecasting accuracy by integrating complex weather data with historical patterns, allowing farmers to anticipate and mitigate the impact of adverse weather conditions on crops.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [91] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    XAI aids regulators in understanding complex AI algorithms, making it easier to detect and prevent biases, discrimination, or unfair practices in areas like loan approvals, hiring, and sentencing.

    “XAI aids regulators in understanding complex AI algorithms, making it easier to detect and prevent biases, discrimination, or unfair practices in areas like loan approvals, hiring, and sentencing.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    The implementation of XAI fosters customer trust and satisfaction and equips retailers to make informed decisions and streamline their operations.

    “The implementation of XAI not only fosters customer trust and satisfaction but also equips retailers to make informed decisions and streamline their operations [13].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [13]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    XAI enhances the effectiveness, efficiency, and equity of education by providing transparent insights, personalized support, and data-driven decision-making tools to educators, students, and families.

    “Overall, XAI enhances the effectiveness, efficiency, and equity of education by providing transparent insights, personalized support, and data-driven decision-making tools to educators, students, and families alike.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    Techniques like layer-wise relevance propagation can help visualize which parts of the input data influenced a neural network's decision.

    “Techniques like layer-wise relevance propagation can help visualize which parts of the input data influenced a neural network's decision.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    Transparency and reasoning from XAI contribute to reducing abandoned products, increasing order value, and boosting revenue and conversion rates.

    “This transparency and reasoning contribute to reducing abandoned products, increasing order value, and consequently boosting revenue and conversion rates, as noted [78].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [78] source

      Not checked in the free run.

63 of 63

  • The paper relies on this without support.

    The banking industry faces challenges in loan acceptance, with rates dropping to 61-70% and further decreasing to 50% post-pandemic, leaving many applicants unaware of the reasons for their rejections, which negatively impacts their credit scores.

    “faces challenges in loan acceptance, with rates dropping to 61-70% and further decreasing to 50% post-pandemic, leaving many applicants unaware of the reasons for their rejections, which negatively impacts their credit scores.”

  • The paper relies on this without support.

    Tax administrations worldwide are increasingly utilizing artificial intelligence (AI) systems for automation.

    “Tax administrations worldwide are increasingly utilizing artificial intelligence (AI) systems for automation.”

  • The paper relies on this without support.

    AI continues to permeate various sectors and industries, and the demand for transparency and interpretability in AI systems has become increasingly pronounced.

    “As Artificial Intelligence (AI) continues to permeate various sectors and industries, the demand for transparency and interpretability in AI systems has become increasingly pronounced.”
3 of 3

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The lack of transparency and interpretability in complex AI models further complicates causal attribution, particularly when AI outputs are integrated into strategic sustainability decisions.

    “Matthew et al. [60] highlights that the lack of transparency and interpretability in complex AI models further complicates causal attribution, particularly when AI outputs are integrated into strategic sustainability decisions.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [60]

    The Introduction (page unavailable) says complex AI models can be difficult to interpret, making it hard to understand how they reach decisions. Section 2 (page unavailable) identifies uncovering cause-and-effect relationships as an aim of explainable AI, and Section 3 discusses explainable AI in sustainable agriculture. The paper does not establish the more specific claim that opacity complicates causal attribution when AI outputs are used in strategic sustainability decisions. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

The citation lists haven’t been fetched yet

References 144 · Cited by 168

Research works printed but not linked: 20

  1. Belghachi M (2023) A review of explainable artificial intelligence methods, applications, and challenges. Indones J Electr Eng Inf (IJEEI) 11(4):1007–1024
  2. Bench-Capon TJ (2014) Knowledge representation: an approach to artificial intelligence (vol 32). Elsevier, Publisher, pp 220
  3. Hanif PM, Soni M, Soni A (2023) A study on the role of artificial intelligence in e-commerce. J Emerg Technol Innov Res 10(9):105–110
  4. Kaushik R (2023) Explainability in machine learning: bridging the gap between model complexity and interpretability. Edu Journal of International Affairs and Research, ISSN: 2583–9993, 2(4), 57–63.
  5. Kumar Y, Jain Y (2012) Research aspects of an expert system. Int J Comput Bus Res 1(11). https://api.semanticscholar.org/CorpusID:61842788
  6. Lawrence B (2019) The role of legal scholars in the development of artificial intelligence. Harv Law Rev Forum 132:157–167
  7. Lee A (2024) Knowledge representation and reasoning in AI: analyzing different approaches to knowledge representation and reasoning in artificial intelligence systems. J Artif Intell Res 4(1):14–29
  8. Lee AVY, Koh E, Looi CK (2023) AI in education and learning analytics in Singapore: an overview of key projects and initiatives. Inf Technol Edu Learn 3(1):Inv-p001
  9. Lim S (2021) Judicial decision-making and explainable artificial intelligence: a reckoning from first principles. Singap Acad Law J 33:280–314
  10. Matcov A (2024) Explainable AI in Credit Risk Assessment for External Customers (Bachelor’s thesis, University of Twente).
  11. Mohammed AA, Ambak K, Mosa AM, Syamsunur D (2019) Expert system in engineering transportation: a review. J Eng Sci Technol 14(1):229–252
  12. Plass M, Kargl M, Kiehl TR, Regitnig P, Geißler C, Evans T, Müller H (2023) Explainability and causability in digital pathology. J Pathol: Clin Res 9(4):251–260
  13. Reshamwala A, Mishra D, Pawar P (2013) Review on natural language processing. IRACST Eng Sci Technol: Int J (ESTIJ) 3(1):113–116
  14. Ryo M (2022) Explainable artificial intelligence and interpretable machine learning for agricultural data analysis. Artif Intell Agric 6:257–265
  15. Schoonderwoerd TA, Jorritsma W, Neerincx MA, Van Den Bosch K (2021) Human-centered XAI: developing design patterns for explanations of clinical decision support systems. Int Lodg Ind: Orig Last Front 154:279–313
  16. Stiglic G, Kocbek P, Fijacko N, Zitnik M, Verbert K, Cilar L (2020) Interpretability of machine learning-based prediction models in healthcare. Wiley Interdiscip Rev: Data Min Knowl Discov 10(5):e1379
  17. Sunitha B, Kiran BK (2023) A systematic review of recommendation systems: applications and challenges. Int J Intell Syst Appl Eng 11(2):826–846
  18. Sutherland A, Wright D (2020) The Governance of Artificial Intelligence in the Legal Sector. AI & Society, 35(1), 119–133. Link
  19. Valavanis KP, Saridis GN (2012) Intelligent robotic systems: theory, design, and applications (vol 182). Springer Science & Business Media.
  20. Vyas B (2023) Explainable AI: assessing methods to make AI systems more transparent and interpretable. Int J New Med Stud: Int Peer Rev Sch Index J 10(1):236–242

Authors
Mathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F.
Affiliations
  • University of Nigeria (NG)
  • Veritas University (NG)
Corresponding author
  • Mathew, Daniel Enemona
  • Ebem, Deborah Uzoamaka
  • Ikegwu, Anayo Chukwu
ORCID
Venue
Neural Processing Letters
Publisher
Springer Science and Business Media LLC
Published
2025-02-07
Volume
57
Issue
1
ISSN
  • 1370-4621 (ISSN-L)
  • 1573-773X
DOI
10.1007/s11063-025-11732-2
OpenAlex
W4407242328
Semantic Scholar
4ed5429cf635af02d36bf9ba69ed3cf61845dc4e
Cited by
168
References
144
Citations by year
2026: 105 · 2025: 63
FWCI
67.38
Type
journal article
Language
en
Open access
Licence
Locations
Neural Processing Letters (publishedVersion, cc-by-nc-nd)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
Keywords
explainable AI, model interpretability, post-hoc explanation, model transparency, interactive visualization, trust in AI, AI accountability, responsible AI deployment, artificial intelligence in healthcare, financial AI

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-08.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-08.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review