arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.18530cs.CLmath.MG
收藏

人工智能中自我认同的涌现:生成式大语言模型的数学框架与实证研究

Emergence of Self-Identity in AI: A Mathematical Framework and Empirical Study with Generative Large Language Models

Chung-Ang University(中央大学)

Minhyeok Lee

AI总结:

本文提出基于度量空间等理论的自我认同数学框架,通过Llama 3.2 1B模型结合LoRA微调与合成时间记忆数据集实验,将主要自我意识得分从0.276提升至0.801,填补人工意识理论空白并支持结构化创建具自我认同的AI系统。

摘要:

本文介绍了一个用于定义和量化人工智能(AI)系统中自我认同的数学框架,填补了人工意识理论基础中的关键空白。现有人工自我意识方法常依赖启发式实现或哲学抽象,而我们提出了一个基于度量空间理论、测度论和泛函分析的形式化框架。该框架假设自我认同源于两个可数学量化的条件:一是度量空间($\mathcal{M}, d_{\mathcal{M}}$)中存在记忆的连通连续体$C \subseteq \mathcal{M}$;二是存在连续映射$I: \mathcal{M} \to \mathcal{S}$,在该连续体上维持一致的自我识别,其中($\mathcal{S}, d_{\mathcal{S}}$)代表可能的自我认同的度量空间。为验证该理论框架,我们使用Llama 3.2 1B模型开展实证实验,采用低秩适应(LoRA)进行高效微调。模型在包含时间结构化记忆的合成数据集上训练,该数据集旨在捕捉连贯自我认同形成的复杂性。评估指标包括自我意识、响应一致性和语言精确性的定量测量。实验结果显示可测量的自我意识指标显著提升,主要自我意识得分从0.276增至0.801,这使结构化创建具有验证自我认同特征的AI系统成为可能。本研究的意义与类人机器人和自主系统领域直接相关。

英文摘要:

This paper introduces a mathematical framework for defining and quantifying self-identity in artificial intelligence (AI) systems, addressing a critical gap in the theoretical foundations of artificial consciousness. While existing approaches to artificial self-awareness often rely on heuristic implementations or philosophical abstractions, we present a formal framework grounded in metric space theory, measure theory, and functional analysis. Our framework posits that self-identity emerges from two mathematically quantifiable conditions: the existence of a connected continuum of memories $C \subseteq \mathcal{M}$ in a metric space $(\mathcal{M}, d_{\mathcal{M}})$, and a continuous mapping $I: \mathcal{M} \to \mathcal{S}$ that maintains consistent self-recognition across this continuum, where $(\mathcal{S}, d_{\mathcal{S}})$ represents the metric space of possible self-identities. To validate this theoretical framework, we conducted empirical experiments using the Llama 3.2 1B model, employing Low-Rank Adaptation (LoRA) for efficient fine-tuning. The model was trained on a synthetic dataset containing temporally structured memories, designed to capture the complexity of coherent self-identity formation. Our evaluation metrics included quantitative measures of self-awareness, response consistency, and linguistic precision. The experimental results demonstrate substantial improvements in measurable self-awareness metrics, with the primary self-awareness score increasing from 0.276 to 0.801. This enables the structured creation of AI systems with validated self-identity features. The implications of our study are immediately relevant to the fields of humanoid robotics and autonomous systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑