World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
42
Citations
13613
World Ranking
8168
National Ranking
3501

Overview

Been Kim is a researcher affiliated with Google in the United States, specializing in computer science with a focus on artificial intelligence and related fields. Their work spans various subfields including artificial intelligence, computer vision and pattern recognition, cognitive neuroscience, economics and econometrics, and materials chemistry. The predominant area of research is artificial intelligence, supported by a substantial volume of publications in this domain.

The main topics addressed by Been Kim include:

  • Explainable Artificial Intelligence (XAI)
  • Adversarial Robustness in Machine Learning
  • Sports Analytics and Performance
  • Machine Learning in Healthcare
  • Artificial Intelligence in Games
  • Machine Learning in Materials Science
  • Bayesian Modeling and Causal Inference

Been Kim has contributed to a variety of publication venues, with a strong presence on arXiv, where most of their work is disseminated. Other frequent venues include the Proceedings of the National Academy of Sciences and Pattern Recognition. The count of publications in some key venues includes arXiv (21), Proceedings of the National Academy of Sciences (3), and Pattern Recognition (1).

Key recent papers by Been Kim include:

  • "Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments" (2021) in Pattern Recognition
  • "Just Say No to Single Embeddings: Why Your AI Needs Multiple Perspectives" (2025) in arXiv (Cornell University)
  • "Concept Bottleneck Models" (2020) in arXiv (Cornell University)
  • "Acquisition of chess knowledge in AlphaZero" (2022) in Proceedings of the National Academy of Sciences
  • "Impossibility theorems for feature attribution" (2024) in Proceedings of the National Academy of Sciences

Been Kim collaborates frequently with several researchers, including Nenad Tomašev, Demis Hassabis, Ulrich Paquet, Thomas McGrath, and Andrei Kapishnikov, each with multiple joint publications. These collaborations contribute to a diverse and interdisciplinary research output.

Best Publications

  • Towards A Rigorous Science of Interpretable Machine Learning

    Finale Doshi-Velez;Been Kim

  • SmoothGrad: removing noise by adding noise

    Daniel Smilkov;Nikhil Thorat;Been Kim;Fernanda B. Viégas

  • Sanity Checks for Saliency Maps

    Julius Adebayo;Justin Gilmer;Michael Christoph Muelly;Ian Goodfellow

  • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

    Been Kim;Martin Wattenberg;Justin Gilmer;Carrie Jun Cai

  • Examples are not enough, learn to criticize! Criticism for Interpretability

    Been Kim;Rajiv Khanna;Oluwasanmi O. Koyejo

  • The (Un)reliability of saliency methods

    Pieter-Jan Kindermans;Sara Hooker;Julius Adebayo;Maximilian Alber

  • A Benchmark for Interpretability Methods in Deep Neural Networks

    Sara Hooker;Dumitru Erhan;Pieter-Jan Kindermans;Been Kim

  • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

    Been Kim;Martin Wattenberg;Justin Gilmer;Carrie Cai

  • Towards Automatic Concept-based Explanations

    Amirata Ghorbani;James Wexler;James Y. Zou;Been Kim

  • Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making

    Carrie J. Cai;Emily Reif;Narayan Hegde;Jason Hipp

  • To Trust Or Not To Trust A Classifier

    Heinrich Jiang;Been Kim;Melody Y. Guan;Maya R. Gupta

  • Learning how to explain neural networks: PatternNet and PatternAttribution

    Pieter Jan Kindermans;Kristof T. Schütt;Maximilian Alber;Klaus Robert Müller

  • The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification

    Been Kim;Cynthia Rudin;Julie A Shah

  • Multiple relative pose graphs for robust cooperative mapping

    Been Kim;Michael Kaess;Luke Fletcher;John Leonard

  • Visualizing and Measuring the Geometry of BERT

    Emily Reif;Ann Yuan;Martin Wattenberg;Fernanda B. Viegas

  • Considerations for Evaluation and Generalization in Interpretable Machine Learning

    Finale Doshi-Velez;Been Kim

  • Concept Bottleneck Models

    Pang Wei Koh;Thao Nguyen;Yew Siang Tang;Stephen Mussmann

  • An Evaluation of the Human-Interpretability of Explanation

    Isaac Lage;Emily Chen;Jeffrey He;Menaka Narayanan

  • Explaining Classifiers with Causal Concept Effect (CaCE).

    Yash Goyal;Amir Feder;Uri Shalit;Been Kim

  • How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation.

    Menaka Narayanan;Emily Chen;Jeffrey He;Been Kim

  • A Roadmap for a Rigorous Science of Interpretability.

    Finale Doshi-Velez;Been Kim

  • Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems

    Shalmali Joshi;Oluwasanmi Koyejo;Warut Vijitbenjaronk;Been Kim

  • Visualizing and Measuring the Geometry of BERT

    Andy Coenen;Emily Reif;Ann Yuan;Been Kim

Frequent Co-Authors

Martin Wattenberg
Martin Wattenberg Harvard University
Finale Doshi-Velez
Finale Doshi-Velez Harvard University
Fernanda B. Viégas
Fernanda B. Viégas Harvard University
Dumitru Erhan
Dumitru Erhan Google (United States)
Cynthia Rudin
Cynthia Rudin Duke University
Joydeep Ghosh
Joydeep Ghosh The University of Texas at Austin
Ian Goodfellow
Ian Goodfellow Google (United States)
Samy Bengio
Samy Bengio Apple (United States)
Samuel J. Gershman
Samuel J. Gershman Harvard University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online pathways in Computer Science can open new doors, especially if you’re seeking flexibility or aiming to balance other commitments. One of the primary considerations for many students is cost. Fortunately, there are affordable online courses that make earning a degree possible without heavy financial burdens.

Not every student has a perfect academic record, but that shouldn’t be a barrier to advancement. If your GPA is a concern, consider the best colleges for low gpa, which offer opportunities to pursue quality degrees with flexible entry requirements.

Though tech roles are plentiful, graduates with a Computer Science or related background can also branch into emerging, high-demand sectors. For example, there are a range of high-paying jobs with environmental science degree credentials, many of them relevant to data analysis, modeling, and sustainability-focused tech solutions.

If you’re eager to accelerate your career and enter the workforce quickly, consider the fast track computer science degree programs. These options are designed to help you complete your studies efficiently, so you can seize tech opportunities sooner.

Best Scientists Citing Been Kim

Trending Scientists