让大模型学会像人一样理解数字的夸张和语境含义
Non-literal Understanding of Number Words by Language Models
- 用理性言语行为框架分解推理过程，定位模型差异点
- 链式思考提示使模型理解更贴近人类，尤其在夸张语境下
- 适合研究认知对齐与自然语言理解的学者参考
人类能自然地非字面理解数字，结合上下文、常识和说话意图。我们探究大语言模型（LLMs）是否具备类似能力，聚焦于夸张表达和语用光环效应。通过与人类数据及语用推理计算模型的系统对比，发现LLMs在理解上与人类存在显著差异。基于理性言语行为（RSA）框架，将语用推理分解为可检验的组件，揭示差异不在于先验知识，而在于如何运用知识。据此提出一种受RSA启发的链式思考提示方法，使模型解释更接近人类。本研究展示了计算认知模型如何诊断人工智能与人类的认知差异，并指导开发更具人类特征的语言理解能力。
原文摘要 · Abstract (English)
Humans naturally interpret numbers non-literally, effortlessly combining context, world knowledge, and speaker intent. We investigate whether large language models (LLMs) interpret numbers similarly, focusing on hyperbole and pragmatic halo effects. Through systematic comparison with human data and computational models of pragmatic reasoning, we find that LLMs diverge from human interpretation in striking ways. By decomposing pragmatic reasoning into testable components, grounded in the Rational Speech Act framework, we pinpoint where LLM processing diverges from human cognition -- not in prior knowledge, but in reasoning with it. This insight leads us to develop a targeted solution -- chain-of-thought prompting inspired by an RSA model makes LLMs' interpretations more human-like. Our work demonstrates how computational cognitive models can both diagnose AI-human differences and guide development of more human-like language understanding capabilities.
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。