PeopleofSuperintelligence

Researcher

Marco Tulio Ribeiro

Also known as Marco Túlio Ribeiro, Marco Ribeiro

Marco Tulio Ribeiro is a researcher at Google DeepMind and an affiliate assistant professor at the University of Washington, where he earned his PhD. He introduced LIME in 2016 to explain classifier predictions locally, then coauthored Anchors in 2018 and CheckList in 2020, which won the ACL Best Paper Award. At Microsoft Research, he coauthored AdaTest, a process that paired people with language models to find and fix bugs in NLP systems. He coauthored a 2023 study of GPT-4 and a July 2025 Microsoft AI paper on sequential medical diagnosis.

Badges

Timeline

  1. 2016

    LIME for classifier explanations

    With Sameer Singh and Carlos Guestrin, he introduces LIME in 2016, a technique that learns an interpretable model locally around a classifier's prediction.

  2. 2018

    A PhD and Anchors

    He completes a PhD at the University of Washington in 2018, advised by Carlos Guestrin and Sameer Singh. With Singh and Guestrin, he introduces Anchors, a system that explains model behavior with high-precision rules based on sufficient conditions.

  3. 2020

    CheckList earns an ACL award

    In 2020, he coauthors CheckList, a task-agnostic method and software for behavioral testing of NLP models. It wins the ACL Best Paper Award.

  4. 2022–2023

    AdaTest at Microsoft Research

    At a February 2023 Stanford seminar, he presents AdaTest as a Senior Researcher at Microsoft Research. The 2022 ACL paper introduces a process that uses language models and human feedback to write unit tests for NLP models.

  5. 2023

    A study of GPT-4

    In 2023, he coauthors a study of an early GPT-4 version that tests its abilities in mathematics, coding, vision, medicine, law, and psychology.

  6. July 2025

    Sequential diagnosis with language models

    In July 2025, he coauthors Sequential Diagnosis with Language Models under a Microsoft AI affiliation. It introduces the Sequential Diagnosis Benchmark and MAI-DxO, an orchestrator for interactive medical reasoning with language models.

  7. As of October 2026

    Researcher at Google DeepMind

    He is a researcher at Google DeepMind and an Affiliate Assistant Professor at the University of Washington.

Career

  1. NowGoogle DeepMindResearcher
  2. NowUniversity of WashingtonAffiliate Assistant Professor
  3. From 2025Microsoft
  4. 2022–2023Microsoft ResearchSenior Researcher

Education

  1. 2018University of WashingtonPhD

From the biography.

  1. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Marco Tulio Ribeiro. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Marco Tulio Ribeiro. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  3. 16% of AI career moves in the 2020s went from a university to a companyIncludes Marco Tulio Ribeiro. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  4. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Marco Tulio Ribeiro. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Marco Tulio Ribeiro yet. Send us a free-licensed photo.

  1. "Why Should I Trust You?": Explaining the Predictions of Any Classifier arxiv.org. Checked 21 October 2026.
  2. Allen School researchers earn Best Paper Award at ACL 2020 news.cs.washington.edu. Checked 21 October 2026.
  3. Anchors: High-Precision Model-Agnostic Explanations ojs.aaai.org. Checked 21 October 2026.
  4. Marco Tulio Ribeiro homes.cs.washington.edu. Checked 21 October 2026.
  5. Beyond Accuracy: Behavioral Testing of NLP Models with CheckList aclanthology.org. Checked 21 October 2026.
  6. Adaptive Testing and Debugging nlp.stanford.edu. Checked 21 October 2026.
  7. Adaptive Testing and Debugging of NLP Models aclanthology.org. Checked 21 October 2026.
  8. Sparks of Artificial General Intelligence: Early experiments with GPT-4 arxiv.org. Checked 21 October 2026.
  9. Sequential Diagnosis with Language Models arxiv.org. Checked 21 October 2026.