Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models
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 impl...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/14/1/44 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589092558209024 |
|---|---|
| author | Minhyeok Lee |
| author_facet | Minhyeok Lee |
| author_sort | Minhyeok Lee |
| collection | DOAJ |
| description | 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>C</mi><mo>⊆</mo><mi mathvariant="script">M</mi></mrow></semantics></math></inline-formula> in a metric space <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="script">M</mi><mo>,</mo><msub><mi>d</mi><mi mathvariant="script">M</mi></msub><mo>)</mo></mrow></semantics></math></inline-formula>, and a continuous mapping <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mo>:</mo><mi mathvariant="script">M</mi><mo>→</mo><mi mathvariant="script">S</mi></mrow></semantics></math></inline-formula> that maintains consistent self-recognition across this continuum, where <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="script">S</mi><mo>,</mo><msub><mi>d</mi><mi mathvariant="script">S</mi></msub><mo>)</mo></mrow></semantics></math></inline-formula> 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 (190.2% improvement) after fine-tuning. In contrast to earlier methods that view self-identity as an emergent trait, our framework introduces tangible metrics to assess and measure artificial self-awareness. 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. Additionally, it opens up new prospects for controlled adjustments of self-identity in contexts that demand different levels of personal involvement. Moreover, the mathematical underpinning of our framework serves as the basis for forthcoming investigations into AI, linking theoretical models to real-world applications in current AI technologies. |
| format | Article |
| id | doaj-art-038c40e4805548b6944a6be8b21ad46b |
| institution | Kabale University |
| issn | 2075-1680 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj-art-038c40e4805548b6944a6be8b21ad46b2025-01-24T13:22:15ZengMDPI AGAxioms2075-16802025-01-011414410.3390/axioms14010044Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language ModelsMinhyeok Lee0School of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, Republic of KoreaThis 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>C</mi><mo>⊆</mo><mi mathvariant="script">M</mi></mrow></semantics></math></inline-formula> in a metric space <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="script">M</mi><mo>,</mo><msub><mi>d</mi><mi mathvariant="script">M</mi></msub><mo>)</mo></mrow></semantics></math></inline-formula>, and a continuous mapping <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mo>:</mo><mi mathvariant="script">M</mi><mo>→</mo><mi mathvariant="script">S</mi></mrow></semantics></math></inline-formula> that maintains consistent self-recognition across this continuum, where <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mi mathvariant="script">S</mi><mo>,</mo><msub><mi>d</mi><mi mathvariant="script">S</mi></msub><mo>)</mo></mrow></semantics></math></inline-formula> 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 (190.2% improvement) after fine-tuning. In contrast to earlier methods that view self-identity as an emergent trait, our framework introduces tangible metrics to assess and measure artificial self-awareness. 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. Additionally, it opens up new prospects for controlled adjustments of self-identity in contexts that demand different levels of personal involvement. Moreover, the mathematical underpinning of our framework serves as the basis for forthcoming investigations into AI, linking theoretical models to real-world applications in current AI technologies.https://www.mdpi.com/2075-1680/14/1/44artificial self-identitylarge language modelsself-awarenessmetric space theorymemory continuumneural adaptation |
| spellingShingle | Minhyeok Lee Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models Axioms artificial self-identity large language models self-awareness metric space theory memory continuum neural adaptation |
| title | Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models |
| title_full | Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models |
| title_fullStr | Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models |
| title_full_unstemmed | Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models |
| title_short | Emergence of Self-Identity in Artificial Intelligence: A Mathematical Framework and Empirical Study with Generative Large Language Models |
| title_sort | emergence of self identity in artificial intelligence a mathematical framework and empirical study with generative large language models |
| topic | artificial self-identity large language models self-awareness metric space theory memory continuum neural adaptation |
| url | https://www.mdpi.com/2075-1680/14/1/44 |
| work_keys_str_mv | AT minhyeoklee emergenceofselfidentityinartificialintelligenceamathematicalframeworkandempiricalstudywithgenerativelargelanguagemodels |