Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge
We present the ARC-DA dataset, a direct-answer (“open response”, “freeform”) version of the ARC (AI2 Reasoning Challenge) multiple-choice dataset. While ARC has been influential in the community,…
GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
Leaderboards have eased model development for many NLP datasets by standardizing their evaluation and delegating it to an independent external repository. Their adoption, however, is so far limited…
CLUE: A Chinese Language Understanding Evaluation Benchmark
We introduce CLUE, a Chinese Language Understanding Evaluation benchmark. It contains eight different tasks, including single-sentence classification, sentence pair classification, and machine…
Belief Propagation Neural Networks
Learned neural solvers have successfully been used to solve combinatorial optimization and decision problems. More general counting variants of these problems, however, are still largely solved with…
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is…
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best…
Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation
We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation…
A Dataset for Tracking Entities in Open Domain Procedural Text
We present the first dataset for tracking state changes in procedural text from arbitrary domains by using an unrestricted (open) vocabulary. For example, in a text describing fog removal using…
A Simple Yet Strong Pipeline for HotpotQA
State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition,…
IIRC: A Dataset of Incomplete Information Reading Comprehension Questions
Humans often have to read multiple documents to address their information needs. However, most existing reading comprehension (RC) tasks only focus on questions for which the contexts provide all…