Building machines that read, learn, and reason.

The Aristo Project aims to build systems that demonstrate a deep understanding of the world, integrating technologies for reading, learning, reasoning, and explanation.

Our research integrates multiple AI technologies, including:

  • Natural language processing
  • Information extraction
  • Knowledge representation
  • Machine reasoning
  • Commonsense knowledge

Aristo Research Areas

Aristo Datasets

To support our research and to engage others in the community, we have developed several machine reasoning datasets that exemplify the various challenges the Aristo team is currently working on. Learn more about each dataset and check out its associated leaderboard:

  • ARC - The AI2 Reasoning Challenge (7,787 multiple choice science questions)
  • OBQA - OpenBook Question Answering, using a "textbook" plus general knowledge
  • ProPara - Comprehending paragraphs that describe a process or procedure
  • QASC - Question-Answering via Sentence Composition, testing multihop QA
  • WIQA - "What if..." questions posed about processes described with a paragraph
  • QuaRel and QuaRTz - Testing understanding of qualitative relationships
  • SciTail - Textual entailment with natural sentences (27k pairs)
  • SciQ - 13k crowdsourced science questions

The Aristo System in 2019

To both drive and showcase our research, we developed the Aristo System for answering real-world science questions. In 2019, the system achieved milestone success on the Grade 8 New York Regents Science Exams, scoring over 90% on the exams' non-diagram, multiple choice (NDMC) questions, where even three years earlier the best systems scored less than 60%. Read more about this in our article From ‘F’ to ‘A’ on the N.Y. Regents Science Exams: An Overview of the Aristo Project, and in the New York Times article A Breakthrough for AI Technology: Passing an 8th Grade Science Test.

Aristo 2019 System Demo

For fun, you can also try competing against a 2016 version of Aristo in our interactive quiz.
“Knowing is not enough, we must apply. Willing is not enough, we must do.”
—  Johann Wolfgang von Goethe