Related papers: Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance

URL: http://arxiv.org/abs/2403.09085v2
Date: Mon, 11 Nov 2024 11:35:28 GMT
Title: Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
Authors: Kai Xiong, Xiao Ding, Ting Liu, Bing Qin, Dongliang Xu, Qing Yang, Hongtao Liu, Yixin Cao,
Abstract summary: Large language models (LLMs) have developed impressive performance and strong explainability across various reasoning scenarios. LLMs often struggle to abstract and apply the generic fact to provide consistent and precise answers. This has sparked a vigorous debate about whether LLMs are genuinely reasoning or merely memorizing.
Score: 38.49506722997423
License:
Abstract: Large language models (LLMs) have developed impressive performance and strong explainability across various reasoning scenarios, marking a significant stride towards mimicking human-like intelligence. Despite this, when tasked with several simple questions supported by a generic fact, LLMs often struggle to abstract and apply the generic fact to provide consistent and precise answers, revealing a deficiency in abstract reasoning abilities. This has sparked a vigorous debate about whether LLMs are genuinely reasoning or merely memorizing. In light of this, we design a preliminary study to quantify and delve into the abstract reasoning abilities of existing LLMs. Our findings reveal a substantial discrepancy between their general reasoning and abstract reasoning performances. To relieve this problem, we tailor an abstract reasoning dataset (AbsR) together with a meaningful learning paradigm to teach LLMs how to leverage generic facts for reasoning purposes. The results show that our approach not only boosts the general reasoning performance of LLMs but also makes considerable strides towards their capacity for abstract reasoning, moving beyond simple memorization or imitation to a more nuanced understanding and application of generic facts. The code is available at https://github.com/Waste-Wood/MeanLearn.