Distinct dynamics of conceptual and referential disruptions in human reading and large language model processing
作者: Rui He, Nihal Altay, Wolfram Hinzen
分类: cs.CL
发布日期: 2026-08-26
💡 一句话要点
研究概念与指称信息在阅读中的动态差异
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 语言处理 概念信息 指称信息 大型语言模型 阅读理解 认知心理学 自然语言处理
📋 核心要点
- 现有研究未能充分区分概念信息与指称信息在语言处理中的不同动态特征。
- 本文通过选择性干扰概念或指称信息，探讨其对人类阅读和语言模型处理的影响。
- 实验结果表明，概念干扰产生局部集中效应，而指称干扰则表现为更分散的处理过程。
📝 摘要（中文）
语言意义根植于概念内容，从中产生对特定实体的指称。为研究这两种意义维度的处理动态，本文选择性地干扰了短叙述中的概念或指称信息，并追踪其在人的自我节奏阅读和大型语言模型处理中的影响。在人类阅读中，概念干扰产生了强烈但局部的处理成本，而指称干扰的效果较弱且逐渐减弱。语言模型中，两种干扰在操控词处立即显现，概念干扰的效果更集中且迅速衰减，而指称干扰则表现出更小且渐进的影响。这些结果为两种意义的可区分处理动态提供了相互印证的证据。
🔬 方法详解
问题定义：本文旨在解决概念信息与指称信息在语言处理中的动态差异问题。现有方法未能有效区分这两者的处理特征，导致对语言理解的认识不足。
核心思路：通过在短叙述中选择性地干扰概念或指称信息，观察其对人类阅读和大型语言模型的影响，从而揭示两种信息处理的动态特征。
技术框架：研究分为两个主要阶段：首先是人类自我节奏阅读实验，其次是大型语言模型的预测与表示处理。每个阶段都通过干扰实验设计来评估不同类型信息的处理效果。
关键创新：本研究的创新在于系统性地比较了概念与指称信息的处理动态，揭示了它们在语言理解中的不同作用机制，这在现有文献中尚属首次。
关键设计：实验中使用了特定的干扰词，设计了自我节奏阅读任务，并在语言模型中应用了上下文模型惊讶度的计算，以捕捉不同干扰对处理的影响。
🖼️ 关键图片
📊 实验亮点
实验结果显示，概念干扰在处理上产生了更大的局部集中效应，而指称干扰则表现为较小且逐渐减弱的影响。具体而言，概念干扰的效果在操控词后迅速达到最大值并快速衰减，而指称干扰的影响则在句子边界处更为明显。
🎯 应用场景
该研究的潜在应用领域包括自然语言处理、教育技术和认知心理学。通过理解概念与指称信息的处理动态，可以优化语言模型的设计，提高机器翻译和文本生成的准确性，同时为语言学习提供更有效的策略。
📄 摘要（原文）
Linguistic meaning is grounded in conceptual content, from which reference to particular entities emerges as words enter discourse. To examine the processing dynamics associated with these two dimensions of meaning, we selectively disrupted conceptual or referential information in short narratives and traced the resulting effects in human self-paced reading and in the predictive and representational processing of large language models. In human reading, conceptual disruptions produced a strong but localized processing cost, emerging immediately after the distorted word, reaching an early maximum, and then declining rapidly. Referential disruptions produced weaker effects, which decreased more gradually across subsequent words, and were more strongly modulated by sentence boundaries. In the language model, both disruptions emerged immediately at the manipulated word. Contextual model surprisal showed a pattern closely paralleling human reading: conceptual disruption produced a larger, more locally concentrated effect that decayed rapidly, whereas referential disruption produced a smaller and more gradual downstream effect. Output-layer representations showed a different pattern: referential disruption produced a larger initial displacement, while both distortions were subsequently characterized by power-law decay. Together, these results provide convergent evidence for distinguishable processing dynamics of two types of meaning: conceptual information imposes a more locally concentrated integration cost, whereas referential information engages a more distributed process of maintaining discourse-level identity.