Information Abstraction for Data Transmission Networks based on Large Language Models

TL;DR

This paper introduces the Degree of Information Abstraction (DIA), a metric for quantifying data compression and semantic preservation, demonstrated through a large language model-guided video transmission case study that achieves 99.75% reduction in data volume.

Contribution

It proposes a formal, information-theoretic framework for measuring and applying information abstraction in data transmission, bridging biological insights and artificial systems.

Findings

DIA effectively quantifies data abstraction and semantic preservation.

Applying DIA to LLM-guided video transmission reduces data volume by 99.75%.

The framework enables energy-efficient and semantically faithful communication systems.

Abstract

Biological systems, particularly the human brain, achieve remarkable energy efficiency by abstracting information across multiple hierarchical levels. In contrast, modern artificial intelligence and communication systems often consume significant energy overheads in transmitting low-level data, with limited emphasis on abstraction. Despite its implicit importance, a formal and computational theory of information abstraction remains absent. In this work, we introduce the Degree of Information Abstraction (DIA), a general metric that quantifies how well a representation compresses input data while preserving task-relevant semantics. We derive a tractable information-theoretic formulation of DIA and propose a DIA-based information abstraction framework. As a case study, we apply DIA to a large language model (LLM)-guided video transmission task, where abstraction-aware encoding significantly reduces transmission volume by $99.75\%$, while maintaining semantic fidelity. Our results suggest that DIA offers a principled tool for rebalancing energy and information in intelligent systems and opens new directions in neural network design, neuromorphic computing, semantic communication, and joint sensing-communication architectures.