The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Edward Y., Kaya, Zeyneb N., Chang, Ethan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917112979652608
author Chang, Edward Y.
Kaya, Zeyneb N.
Chang, Ethan
author_facet Chang, Edward Y.
Kaya, Zeyneb N.
Chang, Ethan
contents We propose semantic anchoring, a unified account of how large language models turn pretrained capacity into goal-directed behavior: external structure (in-context examples, retrieval, or light tuning) binds the model's latent patterns to desired targets. Unified Contextual Control Theory (UCCT) formalizes this via anchoring strength $S = ρ_d - d_r - \log k$, where $ρ_d$ measures target cohesion in representation space, $d_r$ measures mismatch from prior knowledge, and $k$ is the anchor budget. UCCT predicts threshold-like performance flips and strictly generalizes in-context learning, reading retrieval and fine-tuning as anchoring variants. Three controlled studies provide evidence. Experiment 1 demonstrates cross-domain anchoring rebinding strong priors in text and vision. Experiment 2 varies representational familiarity via numeral bases (base-10/8/9) at fixed complexity, yielding ordered thresholds and transfer patterns tracking $ρ_d$, $d_r$, and $S$. Experiment 3 establishes a geometry-to-behavior correlate: layer-wise peak anchoring and trajectory area predict few-shot thresholds $θ_{50}$. UCCT offers testable theory and practical metrics for optimizing prompts, retrieval, and tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning
Chang, Edward Y.
Kaya, Zeyneb N.
Chang, Ethan
Artificial Intelligence
I.2.7
We propose semantic anchoring, a unified account of how large language models turn pretrained capacity into goal-directed behavior: external structure (in-context examples, retrieval, or light tuning) binds the model's latent patterns to desired targets. Unified Contextual Control Theory (UCCT) formalizes this via anchoring strength $S = ρ_d - d_r - \log k$, where $ρ_d$ measures target cohesion in representation space, $d_r$ measures mismatch from prior knowledge, and $k$ is the anchor budget. UCCT predicts threshold-like performance flips and strictly generalizes in-context learning, reading retrieval and fine-tuning as anchoring variants. Three controlled studies provide evidence. Experiment 1 demonstrates cross-domain anchoring rebinding strong priors in text and vision. Experiment 2 varies representational familiarity via numeral bases (base-10/8/9) at fixed complexity, yielding ordered thresholds and transfer patterns tracking $ρ_d$, $d_r$, and $S$. Experiment 3 establishes a geometry-to-behavior correlate: layer-wise peak anchoring and trajectory area predict few-shot thresholds $θ_{50}$. UCCT offers testable theory and practical metrics for optimizing prompts, retrieval, and tuning.
title The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning
topic Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2506.02139