OpenResearchAlpha

International Conference on AI Research · 18 Nov 2026

How Can Artificial Intelligence Explain its Thinking? A Review of Explainable AI

Naren Chandra

0
Citations
no database records one yet
0
Citations in 2026
so far
–
Leading author's h-index
no author has a profile yet
0
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0
  • OpenAlex0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

Artificial Intelligence (AI) systems are increasingly shaping decision-making across industries such as healthcare, finance, e-commerce, education, and cybersecurity. Despite significant advances in machine learning and generative AI, many AI models continue to function as “black boxes,” producing outputs and recommendations without clearly communicating the reasoning behind them. This lack of transparency has raised growing concerns regarding trust, accountability, fairness, and ethical AI adoption. As organizations become more dependent on AI-driven systems, explainability has emerged as a critical factor influencing how users perceive, trust, and adopt artificial intelligence technologies. This literature review examines how Explainable Artificial Intelligence (XAI) enables AI systems to communicate their reasoning in ways understandable to human users. The paper analyzes existing academic and industry research on explainability, transparency, and interpretability within AI systems, with a particular focus on how explanations influence human trust and organizational acceptance of AI technologies. The review evaluates major explainability approaches used in both traditional machine learning models and modern generative AI systems, including techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), attention visualization, counterfactual explanations, and chain-of-thought reasoning methods used in large language models (LLMs). In addition, the paper examines the distinctions between transparency, interpretability, and explainability, and how these concepts contribute to building trustworthy AI systems. The review further analyzes explainability from a human-centered perspective, including perceived fairness, ethical AI design, user confidence, and organizational adoption challenges. The paper also discusses the growing importance of explainability within responsible AI governance frameworks, particularly as regulatory initiatives such as the European Union AI Act increasingly emphasize transparency and accountable AI decision-making. This study contributes to the growing body of literature on explainable AI by consolidating fragmented research on transparency, trust, and human-centered AI adoption. The review identifies current research gaps, limitations of existing explainability approaches, and future opportunities for designing AI systems that are not only accurate and efficient but also understandable, trustworthy, and ethically aligned with human values.

What the data shows

  • No database records a citation yet, as is usual for a paper this new.

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (1)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (0)

What it cites, from open citation data, with Crossref's record of each.

No references in the open citation data yet.
How Can Artificial Intelligence Explain its Thinking? A Review of Explainable AI - QAI OpenResearch