AI People Wiki

Builders & open source

Ranit Aharonov

Co-led IBM Research's Project Debater team and co-wrote its 2021 Nature paper

Ranit Aharonov is the last author of "An autonomous debating system," the 2021 Nature paper describing Project Debater, IBM Research's system for engaging in competitive debate with humans. The paper's contributions statement says Aharonov and Noam Slonim led the team, and that Aharonov helped design and build the system, design its evaluation framework, and write the paper. Aharonov is also listed with IBM Research among the authors of Label Sleuth (2022), an open-source, no-code system for labeling text and building text classifiers.123

At a glance

Current role
None confirmed in the sources
Work listed
2
Sources cited
9
Profile reviewed

Project Debater

Aharonov co-led, with Noam Slonim, the IBM Research team behind Project Debater, a system designed to take part in competitive debate with humans. According to the contributions statement of the 2021 Nature paper "An autonomous debating system", on which Aharonov is last author, Aharonov helped design and build the system, designed its evaluation framework, and wrote the paper with Slonim and Yonatan Bilu.1

Aharonov also co-authored related argument-mining papers with Slonim and colleagues, including work on corpus-wide argument mining (2019), a large dataset for ranking the quality of arguments (2019), and an overview of the 2021 Key Point Analysis shared task held at the Workshop on Argument Mining at EMNLP 2021.456

Research

Aharonov's other language-technology papers cover explainability, summarization and text classification. Aharonov co-authored a 2020 survey of explainable AI for natural language processing, TWEETSUMM (2021), a dialog summarization dataset for customer service, and Cluster & Tune (2022), which improves text classification when labeled data is scarce by adding an intermediate unsupervised clustering task. Aharonov is also among the authors of Label Sleuth (2022), an open-source, no-code tool for labeling text and building classifiers.78923

Work and contributions

  • Project Debater Published research

    Last author of "An autonomous debating system" (Nature, 2021). The contributions statement says Aharonov designed and built Project Debater with the team, designed the evaluation framework, wrote the paper with Noam Slonim and Yonatan Bilu, and co-led the team with Slonim.1

  • Label Sleuth Open-source code

    Listed among the authors of "Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours" (2022), which introduces a free, open-source, no-code system for labeling text and creating classifiers; the label-sleuth repository is under the Apache-2.0 license.23

Timeline

  1. Co-authored "A Large-scale Dataset for Argument Quality Ranking" and a paper on corpus-wide argument mining.54
  2. Co-authored "A Survey of the State of Explainable AI for Natural Language Processing".7
  3. Published "An autonomous debating system" in Nature as last author, describing Project Debater.1
  4. Co-authored the overview of the 2021 Key Point Analysis shared task.6
  5. Co-authored TWEETSUMM, a dialog summarization dataset for customer service, as last author.8
  6. Co-authored "Cluster & Tune", on boosting cold-start text classification.9
  7. Co-authored Label Sleuth, an open-source no-code system for text classification.2

Documented roles

The sources do not confirm a current role; these are the roles they document.

  • Co-leader of the Project Debater team, listed with IBM Research AI on the 2021 Nature paper and with IBM Research on the 2022 Label Sleuth paper, IBM Research12

Companies in their history

  • IBM 29 people in the wiki

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

9 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. An autonomous debating system (Nature 591, 2021)Nature · Paper · published Mar 17, 2021 · accessed Oct 21, 2026
  2. Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours (arXiv 2208.01483)arXiv · Paper · published Aug 2, 2022 · accessed Oct 21, 2026
  3. label-sleuth/label-sleuth README and license (Apache-2.0)Label Sleuth (GitHub repository) · Repository · accessed Oct 21, 2026
  4. Corpus Wide Argument Mining -- a Working Solution (arXiv 1911.10763)arXiv · Paper · published Nov 25, 2019 · accessed Oct 21, 2026
  5. A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis (arXiv 1911.11408)arXiv · Paper · published Nov 26, 2019 · accessed Oct 21, 2026
  6. Overview of the 2021 Key Point Analysis Shared Task (arXiv 2110.10577)arXiv · Paper · published Oct 20, 2021 · accessed Oct 21, 2026
  7. A Survey of the State of Explainable AI for Natural Language Processing (arXiv 2010.00711)arXiv · Paper · published Oct 1, 2020 · accessed Oct 21, 2026
  8. TWEETSUMM -- A Dialog Summarization Dataset for Customer Service (arXiv 2111.11894)arXiv · Paper · published Nov 23, 2021 · accessed Oct 21, 2026
  9. Cluster & Tune: Boost Cold Start Performance in Text Classification (arXiv 2203.10581)arXiv · Paper · published Mar 20, 2022 · accessed Oct 21, 2026