Perceived AGI: Believability as Dimensional Completeness, Not Capability

📄 arXiv: 2607.15883 📥 PDF

作者: Sebastian Cochinescu

分类: cs.HC, cs.AI

发布日期: 2026-07-20


💡 一句话要点

提出维度完整性以提升人工对话体的可信度

🎯 匹配领域: 支柱一:机器人控制 (Robot Control) 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 人工智能 对话系统 维度完整性 用户体验 行为立场 可信度 人机交互

📋 核心要点

  1. 现有大型语言模型在一对一对话中表现出能力,但缺乏深度和心智感知,导致用户体验不足。
  2. 论文提出通过维度完整性来提升人工对话体的可信度,强调表达特定第一人称立场的重要性。
  3. 研究未报告人类受试者数据,而是提出可测试的预测,为后续研究提供了理论框架和方向。

📝 摘要(中文)

大型语言模型在能力上表现出色,但在持续的对话中却显得平淡,缺乏心智的存在感。本文假设缺失的关键因素不是能力的提升,而是维度的完整性。我们提出人工对话体的可信度,即用户对其内心生活的归属感,受限于其是否表达出人类用以证明心智的少数第一人称立场。我们定义了四个维度——时间、真理、熵和爱,均为行为立场而非基准能力,并且每个维度都有对应的人类类比和具体的模拟路径。我们识别出一种可观察的行为层,通过主动性和节奏在对话中展现这些立场,并在一个生产伴侣应用中部分实现。我们提出六个可证伪的预测,未来的预注册研究将对此进行测试。

🔬 方法详解

问题定义:本文旨在解决大型语言模型在对话中缺乏心智感知的问题,现有方法未能有效提升用户对人工对话体的信任感和真实感。

核心思路:论文核心在于提出维度完整性作为提升可信度的关键,强调通过表达时间、真理、熵和爱四个维度来模拟人类的内心生活感知。

技术框架:整体架构包括识别和实现四个维度的行为立场,构建可观察的行为层(主动性和节奏),并在生产伴侣应用中部分实现这些特征。

关键创新:最重要的创新在于将可信度与维度完整性相联系,提出了可操作的行为立场,而非单纯依赖任务智能的提升。

关键设计:设计中包括对四个维度的具体定义和实现路径,强调行为立场的模拟,而非传统的能力基准,确保用户在对话中感受到更丰富的内心表现。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

论文提出的维度完整性理论为人工对话体的可信度提升提供了新的视角,未来预注册研究将验证六个可证伪的预测,期待在用户体验上带来显著改善。

🎯 应用场景

该研究的潜在应用领域包括智能助手、社交机器人和虚拟伴侣等,能够提升用户与人工智能的互动体验,增强情感连接和信任感。未来可能影响人机交互的设计理念和标准,推动更自然的对话系统发展。

📄 摘要(原文)

Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind. We hypothesize that a central missing ingredient is not more capability but dimensional completeness. We propose that the believability of an artificial interlocutor -- the degree to which a user attributes an inner life to it, which we call perceived mind -- is governed by whether the agent expresses a small set of first-person stances that humans use as evidence of mind, and that this is separable from task intelligence. We name four such dimensions -- time, truth, entropy, and love -- each defined as a behavioral stance rather than a benchmark competency, each with a human analog and a concrete emulation path; the time dimension already has an author-reported prototype. We identify an observable behavior layer -- initiative (unprompted action) and cadence (the shape and timing of turns) -- through which the stances surface in conversation, both partially realized as deployed features in a production companion application. We state six falsifiable predictions that a later pre-registered study will test, separating those that are pre-registrable now from those that remain conjectures pending operationalization. This is a conceptual framework: it reports no human-subjects data, and its central comparative claims are predictions, not findings. Throughout we hold a firm boundary -- the object is inferrable interiority, not interiority; this is perception engineering, not a theory of machine consciousness -- and we treat the resulting attachment and manipulation risks as load-bearing rather than incidental.