mlsanityData to 14 Oct 2026

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

arXiv 2506.02139 ↗First posted 2 Jun 2025cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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 = ρd - dr - log k, where ρd measures target cohesion in representation space, dr 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 ρd, dr, and S. Experiment 3 establishes a geometry-to-behavior correlate: layer-wise peak anchoring and trajectory area predict few-shot thresholds θ50. UCCT offers testable theory and practical metrics for optimizing prompts, retrieval, and tuning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 10 of its 26 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

10 of 26 references.

References · 10

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2023Progress measures for grokking via mechanistic interpretabilitycited by 839
  4. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
  5. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  6. 2024OpenCoder: The Open Cookbook for Top-Tier Code Large Language Modelscited by 130
  7. 2024Competition Dynamics Shape Algorithmic Phases of In-Context Learningcited by 54
  8. 2024ICLR: In-Context Learning of Representationscited by 50
  9. 2025Test-Time Learning for Large Language Modelscited by 50
  10. 2024Loss Landscape Degeneracy and Stagewise Development in Transformerscited by 40

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
  2. 2026Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs
  3. 2025Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
  4. 2025Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
  5. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
  6. 2022Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale
  7. 2025Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations
  8. 2025Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context