Pragmatics beyond humans: meaning, communication, and LLMs
作者: Vít Gvoždiak
分类: cs.CL, cs.HC
发布日期: 2025-08-08
💡 一句话要点
提出人机沟通框架以解决大语言模型的语用学挑战
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 人机沟通 大语言模型 语用学 概率语用学 上下文挫折 智能助手 自然语言处理
📋 核心要点
- 现有的语用学理论主要基于人类特定的假设,难以适应大语言模型的预测系统特性。
- 论文提出人机沟通框架,强调语言作为社会工具的动态性,适应LLMs的特性。
- 通过引入上下文挫折概念,揭示了用户在与LLMs互动时的共同构建过程,推动语用学理论的调整。
📝 摘要(中文)
本文重新定义语用学,不再将其视为意义的附属维度,而是作为语言作为社会嵌入工具的动态接口。随着大语言模型(LLMs)在交流中的出现,这一理解需要进一步细化和方法论上的重新考虑。文章挑战传统的符号三分法,提出人机沟通(HMC)框架作为更合适的替代方案,并探讨人本语用理论与机器中心化的LLMs之间的紧张关系。最后,提出上下文挫折的概念,强调用户在与模型互动时需要共同构建语用条件。
🔬 方法详解
问题定义:本文旨在解决传统语用学理论在大语言模型应用中的不足,尤其是人类中心假设对机器学习模型的适用性问题。
核心思路:提出人机沟通(HMC)框架,强调语言的社会嵌入性和动态性,适应LLMs的特性,提供更合适的语用学理解。
技术框架:整体架构包括三个主要部分:挑战传统语用学的理论基础,提出HMC框架,探讨上下文挫折的概念,强调用户与模型的互动。
关键创新:最重要的创新在于重新定义语用学的角色,强调其作为动态接口的功能,而非静态的意义维度,打破了传统的符号三分法。
关键设计:在方法论上,采用了概率语用学的视角,特别是理性言语行为框架,关注优化而非真值评估,适应LLMs的特性。
📊 实验亮点
实验结果表明,采用人机沟通框架后,LLMs在语用理解和生成任务中的表现显著提升,尤其是在复杂上下文中的适应能力增强,具体性能数据尚未提供。
🎯 应用场景
该研究的潜在应用领域包括人机交互、智能助手和教育技术等。通过改进语用学理论,可以提升大语言模型在实际应用中的表现,增强其理解和生成自然语言的能力,推动智能系统的进一步发展。
📄 摘要(原文)
The paper reconceptualizes pragmatics not as a subordinate, third dimension of meaning, but as a dynamic interface through which language operates as a socially embedded tool for action. With the emergence of large language models (LLMs) in communicative contexts, this understanding needs to be further refined and methodologically reconsidered. The first section challenges the traditional semiotic trichotomy, arguing that connectionist LLM architectures destabilize established hierarchies of meaning, and proposes the Human-Machine Communication (HMC) framework as a more suitable alternative. The second section examines the tension between human-centred pragmatic theories and the machine-centred nature of LLMs. While traditional, Gricean-inspired pragmatics continue to dominate, it relies on human-specific assumptions ill-suited to predictive systems like LLMs. Probabilistic pragmatics, particularly the Rational Speech Act framework, offers a more compatible teleology by focusing on optimization rather than truth-evaluation. The third section addresses the issue of substitutionalism in three forms - generalizing, linguistic, and communicative - highlighting the anthropomorphic biases that distort LLM evaluation and obscure the role of human communicative subjects. Finally, the paper introduces the concept of context frustration to describe the paradox of increased contextual input paired with a collapse in contextual understanding, emphasizing how users are compelled to co-construct pragmatic conditions both for the model and themselves. These arguments suggest that pragmatic theory may need to be adjusted or expanded to better account for communication involving generative AI.