Analogical reasoning is a fundamental cognitive ability of humans. However, current language models (LMs) still struggle to achieve human-like performance in analogical reasoning tasks due to a lack of resources for model training. In this work, we address this gap by proposing ANALOGYKB, a million-scale analogy knowledge base (KB) derived from existing knowledge graphs (KGs). ANALOGYKB identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large language models (LLMs), followed by minor human efforts for data quality control. Evaluations on a series of datasets of two analogical reasoning tasks (analogy recognition and generation) demonstrate that ANALOGYKB successfully enables both smaller LMs and LLMs to gain better analogical reasoning capabilities.
@article{arxiv.2305.05994,
title = {ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base},
author = {Siyu Yuan and Jiangjie Chen and Changzhi Sun and Jiaqing Liang and Yanghua Xiao and Deqing Yang},
journal= {arXiv preprint arXiv:2305.05994},
year = {2024}
}