测试大模型对概念组合中属性变化的理解能力
Is a Peeled Apple Still Red? Evaluating LLMs' Ability for Conceptual Combination with Property Type
- 构建12.3K三元组数据集，区分属性继承、涌现与消失三种类型
- 发现o1等模型难以生成具有新属性的名词短语
- 基于认知心理学方法提升生成效果，适合研究认知推理者
概念组合是将基本概念融合以生成复杂表达的认知过程，其属性可能继承、新出现或被抵消。现有研究仅覆盖有限属性且未考察生成过程。为此，我们提出概念组合属性类型数据集（CCPT），包含12.3K个带标注的名词短语-属性-属性类型三元组。基于此，我们设立三类评估任务，全面检验大模型在概念组合中的表现。主要发现：(1) 自动度量的属性涌现与抵消与人类判断高度一致；(2) 包括OpenAI o1在内的大模型在生成具备给定涌现属性的名词短语时表现不佳；(3) 受认知心理学模型启发的方法，在所有生成任务中均显著提升性能。数据集与代码已开源。
原文摘要 · Abstract (English)
Conceptual combination is a cognitive process that merges basic concepts, enabling the creation of complex expressions. During this process, the properties of combination (e.g., the whiteness of a peeled apple) can be inherited from basic concepts, newly emerge, or be canceled. However, previous studies have evaluated a limited set of properties and have not examined the generative process. To address this gap, we introduce the Conceptual Combination with Property Type dataset (CCPT), which consists of 12.3K annotated triplets of noun phrases, properties, and property types. Using CCPT, we establish three types of tasks to evaluate LLMs for conceptual combination thoroughly. Our key findings are threefold: (1) Our automatic metric grading property emergence and cancellation closely corresponds with human judgments. (2) LLMs, including OpenAI's o1, struggle to generate noun phrases which possess given emergent properties. (3) Our proposed method, inspired by cognitive psychology model that explains how relationships between concepts are formed, improves performances in all generative tasks. The dataset and experimental code are available at https://github.com/seokwon99/CCPT.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。