@inproceedings{6cc43625effd4347aa627182499e2821,
title = "CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm",
abstract = "We propose a new commonsense reasoning benchmark to motivate commonsense reasoning progress from two perspectives: (1) Evaluating whether models can distinguish knowledge quality by predicting if the knowledge is enough to answer the question; (2) Evaluating whether models can develop commonsense inference capabilities that generalize across tasks. We first extract supporting knowledge for each question and ask humans to annotate whether the auto-extracted knowledge is enough to answer the question or not. After that, we convert different tasks into a unified question-answering format to evaluate the models{\textquoteright} generalization capabilities. We name the benchmark Commonsense Inference with Knowledge-in-the-loop Question Answering (CIKQA). Experiments show that with our learning paradigm, models demonstrate encouraging generalization capabilities. At the same time, we also notice that distinguishing knowledge quality remains challenging for current commonsense reasoning models.",
author = "Hongming Zhang and Yintong Huo and Yanai Elazar and Yangqiu Song and Yoav Goldberg and Dan Roth",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 ; Conference date: 02-05-2023 Through 06-05-2023",
year = "2023",
month = jan,
day = "1",
language = "American English",
series = "EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023",
publisher = "Association for Computational Linguistics (ACL)",
pages = "114--124",
booktitle = "EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023",
address = "United States",
}