跨学科误解分类与建模：从语用学到AI代理的生成、放大与检测
原标题：Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents
AI 摘要
该论文提出了一种跨学科的误解分类法，将误解视为生成、放大、检测与修复的分层过程，整合了九个领域的研究，识别出十一种失败模式，并将其映射到八个分析层。作者对八个层进行了形式化建模，扩展了信息与通信理论，从信号传输延伸到意义重建，并提供了证据矩阵、编码手册和九个对话案例。研究强调，随着AI代理介入人际沟通，误解的检测变得更加紧迫，因为AI系统缺乏自我纠错能力，且人们在与AI交互时更少主动修复误解。
正文节选
[Page 1] Cross -Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents Babak Abbaschian University of Louisville ORCID: https://orcid.org/0000-0003-4876-9372 Abstract Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasingly handled by AI-mediated channels. This shift cuts communicators off from the resources repair