Explainable Artificial Intelligence (XAI)
Explainable Artificial Intelligence (XAI) is a research topic within Artificial Intelligence. Science Explorer counts 16k research works in it since 1965. 23.8% of them reached the world's top 10% most cited for their field and year.
This cluster of papers focuses on Explainable Artificial Intelligence (XAI) and the development of interpretable models, visual explanations, and responsible machine learning interpretability. It explores concepts, challenges, and opportunities in XAI, including the use of gradient-based localization, understanding deep neural networks, feature importance, and addressing black box models. The papers also discuss the responsibility and ethical considerations in AI.
- Interpretable Models
- Machine Learning Interpretability
- Visual Explanations
- XAI Concepts
- Model Interpretability
- Gradient-Based Localization
- Deep Neural Networks
- Feature Importance
- Black Box Models
- Responsibility in AI
- Research works
- 16k fractional, since 1965
- In the world top 10%
- 3.9k per year above
- Top-10% rate
- 23.8% share of its works in the world top 10%
- Growth, 2013–17 → 2018–22
- +1002% the tick is no change
Which countries lead Explainable Artificial Intelligence (XAI) research?
By volume, the United States and China publish the most (2k and 875 works in 2022–2025).
By volume, 2022–2025
- 1 United States 2k works
- 2 China 875 works
- 3 India 817 works
- 4 Germany 582 works
- 5 United Kingdom 498 works
- 6 Italy 353 works
- 7 Canada 261 works
- 8 Australia 224 works
- 9 France 215 works
- 10 Spain 186 works
How concentrated that is
The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.
Shares of the rows listed above, not of the whole node.
Which institutions lead Explainable Artificial Intelligence (XAI) research?
By volume in 2022–2025, Design Intelligence (United States) publishes the most Explainable Artificial Intelligence (XAI) research, followed by Carnegie Mellon University and Stanford University.
By volume, 2022–2025
- 1 Design Intelligence (United States) United States 49 works
- 2 Carnegie Mellon University United States 35 works
- 3 Stanford University United States 30 works
- 4 Delft University of Technology Netherlands 30 works
- 5 Imperial College London United Kingdom 28 works
- 6 Georgia Institute of Technology United States 27 works
- 7 National University of Singapore Singapore 25 works
- 8 University of Washington United States 25 works
- 9 Centre National de la Recherche Scientifique France 22 works
- 10 University of Oxford United Kingdom 22 works
Who are the leading researchers in Explainable Artificial Intelligence (XAI)?
The most-cited researchers publishing on Explainable Artificial Intelligence (XAI) include Yoshua Bengio, Olga Russakovsky and Quoc V. Le.
- 1 Yoshua Bengio 17k citations
- 2 Olga Russakovsky 8.9k citations
- 3 Quoc V. Le 8.6k citations
- 4 Bernt Schiele 6.9k citations
- 5 Trevor Darrell 6.7k citations
- 6 Francisco Herrera 6.5k citations
Ranked by citations received across their whole record, among researchers with at least three works on this topic.
Where is Explainable Artificial Intelligence (XAI) research done?
The largest centres of Explainable Artificial Intelligence (XAI) research in 2022–2025 are Beijing (China), London (United Kingdom), Seoul (South Korea) and New York (United States). Among places with at least 20 works in it, it is an unusually large share of all research in Norman.
Largest cities, 2022–2025
Where it is the local speciality
- NormanUS · 54.1 works19×
Location quotient: how much more of its research is in Explainable Artificial Intelligence (XAI) than the world average.
Where is the best place to study Explainable Artificial Intelligence (XAI)?
Among universities, judged by research, Carnegie Mellon University, Delft University of Technology and University College London score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.
One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.
| # | University | Score | Top 10% | Specialisation | Works | Growth |
|---|---|---|---|---|---|---|
| 1 | Carnegie Mellon University United States | 78.5 | 37.1% | 10.2× | 35 | +410.7% |
| 2 | Delft University of Technology Netherlands | 59.5 | 40.0% | 5.4× | 30 | — |
| 3 | University College London United Kingdom | 59.2 | 44.9% | 1.9× | 22 | +483.2% |
| 4 | Massachusetts Institute of Technology United States | 57.9 | 37.5% | 3.9× | 20 | +254.4% |
| 5 | Singapore Management University Singapore | 57.9 | 31.7% | 12.4× | 11 | — |
| 6 | Paderborn University Germany | 57.8 | 44.4% | 9.4× | 11 | — |
| 7 | University of Oxford United Kingdom | 56.8 | 40.1% | 2.1× | 22 | +494.6% |
| 8 | University of Pavia Italy | 53.3 | 53.0% | 5.0× | 11 | — |
| 9 | University of Pisa Italy | 51.8 | 34.0% | 5.7× | 22 | — |
| 10 | Cornell University United States | 51.4 | 37.6% | 2.2× | 18 | +374.7% |
Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.
Is Explainable Artificial Intelligence (XAI) research growing?
Output in 2018–2022 was 1002% higher than in 2013–2017, peaking in 2026. The fastest-growing topics are Explainable Artificial Intelligence (XAI).
The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.
Which topics inside it are moving
Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.