提出用户意图的计算框架，揭示了对话中隐藏的意图层
Intent Signal Theory: A Computational Framework for Intent-State Control in Human-AI Interaction
- 将用户意图分为潜藏意图、可观测代理、编码载体和模型输出四类
- 发现私有意图一旦丢失就无法恢复，仅能用通用替代
- 适用于想理解人机交互深层机制的研究者
当前的人工智能交互模型将提示词视为主要交换对象，忽略了关键的一层：用户的潜在源意图，即提示词前驱且驱动提示的目标状态。本文提出意图信号理论（Intent Signal Theory, IST），构建了这一缺失意图层的计算框架。IST明确区分四个常被混淆的实体：潜藏源意图（I*）、可观测意图代理（I-hat）、编码载体（P）和模型输出（O）。该理论形式化了维度权重、编码掩码、结构与保真度恢复评分，以及公开-私有意图分解。不可逆意图损失定理指出，若私有意图未被载体包含，则无法超越泛化替代进行恢复。四项配套研究涵盖六种大语言模型、三种语言和三个任务领域，结果表明结构-保真度分离、人工验证的指标解耦及权重容忍平台，均与IST预测一致。IST将提示工程重构为意图协议设计，并揭示了当前人工智能系统所缺乏的计算层级。
原文摘要 · Abstract (English)
Current AI interaction models treat the prompt as the primary object of exchange, omitting a critical layer: the user's latent source intent, the goal state preceding and motivating the prompt. Here we introduce Intent Signal Theory (IST), a computational framework that formalises this missing intent layer. IST distinguishes four objects routinely conflated: latent source intent (I*), observable intent proxy (I-hat), encoded carrier (P), and model output (O). It formalises dimensional weights, encoding masks, structural and fidelity recovery scores, and public-private intent decomposition. The Theorem of Irreversible Intent Loss establishes that private intent absent from the carrier cannot be recovered beyond generic substitution. Evidence from four companion studies spanning six LLMs, three languages and three task domains shows structural-fidelity splits, human-validated metric dissociation, and weight-tolerance plateaus consistent with IST's predictions. IST reframes prompt engineering as intent-protocol design and identifies a computational layer that current AI systems lack.
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。