Featured Demos
A computational model for descriptive ethics | MosaicDelphi is intended to study the promises and limitations of machine ethics and norms through the lens of descriptive ethics, i.e., people’s moral judgments on a variety of everyday situations
Try the demo
Several demos of a variety of popular computer vision models | PRIORThe Computer Vision Explorer lets you try and compare a variety of popular computer vision models related to recognition, vision and language, human-centric vision, and scene geometry tasks. Use our example images or try with your own.
Try the demo
Generating Implications, Proofs, and Abductive Statements over Natural Language | AristoLike RuleTaker, ProofWriter determines whether statements are True or False based on rules given in natural language - but also generates the proof of its answers.
Try the demo
Modular QA answers questions by breaking them down into a series of smaller, more specific ones. This produces answers in a human-like way that's more explainable than black-box systems. | AristoModularQA is a neuro-symbolic question-answering system that answers complex questions by asking a series of sub-questions to existing simpler QA systems or symbolic modules. It explains each of its reasoning steps in language, in terms of a simple question and its answer as produced by a simpler model or a math…
Try the demo
Uncovering stereotypical biases via underspecified questions | AristoThis work focuses specifically on identifying biases in question answering (QA) models. If these models are blindly deployed in real-life settings, the biases within these models could cause real harm, which raises the question; how extensive are social stereotypes in question-answering models?
Try the demo
Evaluating neural toxic degeneration in language models | MosaicIn new joint work at AI2 and UW, we study how often popular NLP components produce problematic content, what might trigger this neural toxic degeneration from a given system, and whether or not it can be successfully avoided. We also study how much toxicity is present in the web text that these systems learned…
Try the demo
Find out whether scientific research supports or refutes a given claim | Semantic ScholarOur fact verification demo was built using the SciFact dataset, a collection of 1.4K expert-written scientific claims paired with evidence-containing abstracts, and annotated with labels and rationales.
Try the demo
Crossing format boundaries with a single QA system | AristoUnifiedQA is a single pre-trained QA model that performs surprisingly well across 17 QA datasets spanning 4 diverse formats. Fine-tuning UnifiedQA into specialized models results in a new state-of-the-art on 6 datasets, establishing this model as a strong starting point for building QA systems.
Try the demo
Exploring the evolving network of science in CORD-19 | Semantic ScholarUse our exploratory search tools to find out what groups are working on what directions, see how biomedical concepts interact and evolve over time, and discover new connections.
Try the demo
Transformers as Soft Reasoners over Language | AristoRuleTaker determines whether statements are True or False based on rules given in natural language.
Try the demo
