@inproceedings{9304613f5aca472b84a51d592fe42369,
title = "ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies",
abstract = "Analogy-making is central to human cognition, allowing us to adapt to novel situations – an ability that current AI systems still lack. Most analogy datasets today focus on simple analogies (e.g., word analogies); datasets including complex types of analogies are typically manually curated and very small. We believe that this holds back progress in computational analogy. In this work, we design a data generation pipeline, ParallelPARC (Parallel Paragraph Creator) leveraging state-of-the-art Large Language Models (LLMs) to create complex, paragraph-based analogies, as well as distractors, both simple and challenging. We demonstrate our pipeline and create ProPara-Logy, a dataset of analogies between scientific processes. We publish a gold-set, validated by humans, and a silver-set, generated automatically. We test LLMs{\textquoteright} and humans{\textquoteright} analogy recognition in binary and multiple-choice settings, and found that humans outperform the best models (∼13% gap) after a light supervision. We demonstrate that our silver-set is useful for training models. Lastly, we show challenging distractors confuse LLMs, but not humans. We hope our pipeline will encourage research in this emerging field.",
author = "Oren Sultan and Yonatan Bitton and Ron Yosef and Dafna Shahaf",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024 ; Conference date: 16-06-2024 Through 21-06-2024",
year = "2024",
language = "الإنجليزيّة",
series = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024",
publisher = "Association for Computational Linguistics (ACL)",
pages = "5900--5924",
editor = "Kevin Duh and Helena Gomez and Steven Bethard",
booktitle = "Long Papers",
address = "الولايات المتّحدة",
}