Information Abstraction for Data Transmission Networks based on Large Language Models

2026-02-11

AI Summary

This work addresses the high energy consumption of modern communication systems in low-level data transmission and their lack of explicit modeling of information abstraction, which hinders the joint optimization of semantic fidelity and efficiency. To this end, the paper introduces the first computable metric for Degree of Information Abstraction (DIA), establishes a multi-level abstraction framework grounded in information theory, and integrates large language models to enable semantic-aware video coding. By performing task-oriented semantic-preserving compression, the proposed method achieves a 99.75% reduction in transmitted data volume while maintaining high semantic fidelity. This approach establishes a new paradigm for energy-efficient intelligent communication systems that prioritize semantic relevance over raw data fidelity.

Technology Category

• Machine Learning: Information Theory
• Computer Vision: Large Vision Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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.

Problem

• information abstraction
• energy efficiency
• semantic communication
• data transmission
• computational theory

Innovation

• Degree of Information Abstraction
• semantic communication
• large language models
• information-theoretic formulation
• data compression