Abstraction ability is crucial in human intelligence, which can also benefit
various tasks in NLP study. Existing work shows that LLMs are deficient in
abstract ability, and how to improve it remains unexplored. In this work, we
design the framework AbsInstruct to enhance LLMs' abstraction ability through
instruction tuning. The framework builds instructions with in-depth
explanations to assist LLMs in capturing the underlying rationale of
abstraction. Meanwhile, we introduce a plausibility estimator to select
instructions that are more consistent with the abstraction knowledge of LLMs to
be aligned. Then, our framework combines abstraction instructions with
general-purpose ones to build a hybrid dataset. Extensive experiments and
analyses demonstrate that our framework can considerably enhance LLMs'
abstraction ability with strong generalization performance while maintaining
their general instruction-following abilities.

通过指导调整的方式，我们提出了 AbsInstruct 框架来增强 LLMs 的抽象能力，通过深入解释构建指导，以帮助 LLMs 抓住抽象的基本原理，并使用可能性估计器选择与 LLMs 的抽象知识更一致的指导，将抽象指导与通用指导结合构建混合数据集，在保持其通用指导遵循能力的同时，大大提高了 LLMs 的抽象能力和强大的推广性能。

AbsInstruct: 通过解释调整和可信度估计从 LLMs 中调动抽象能力

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation  Tuning with Plausibility Estimation

Cognitive research indicates that abstraction ability is essential in human
intelligence, which remains under-explored in language models. In this paper,
we present AbsPyramid, a unified entailment graph of 221K textual descriptions
of abstraction knowledge. While existing resources only touch nouns or verbs
within simplified events or specific domains, AbsPyramid collects abstract
knowledge for three components of diverse events to comprehensively evaluate
the abstraction ability of language models in the open domain. Experimental
results demonstrate that current LLMs face challenges comprehending abstraction
knowledge in zero-shot and few-shot settings. By training on our rich
abstraction knowledge, we find LLMs can acquire basic abstraction abilities and
generalize to unseen events. In the meantime, we empirically show that our
benchmark is comprehensive to enhance LLMs across two previous abstraction
tasks.

本研究通过引入 AbdPyramid，一个包含 22.1 万个抽象知识描述的统一蕴含图，全面评估了语言模型在开放领域中的抽象能力。实验结果表明，现有的语言模型面临着在零样本和少样本情况下理解抽象知识的挑战，并且通过在我们的丰富的抽象知识上进行训练，语言模型可以获得基本的抽象能力并推广到未见过的事件。同时，我们的基准实证显示能够全面增强语言模型在之前的抽象任务中的性能。