Semantic Caching for Improving Web Affordability

2025-06-25

AI Summary

Rising web scale exacerbates network burdens in developing countries, where high data costs constrain accessibility. To address this, we propose a large language model (LLM)-based semantic caching framework that transcends conventional exact-match caching by leveraging multimodal LLMs (GPT-4o and LLaMA 3.1) to assess semantic substitutability of images—enabling reuse while preserving visual fidelity. Our end-to-end architecture integrates user-configurable policies and privacy-preserving mechanisms. Empirical evaluation across 50 mainstream news websites demonstrates up to 37% image substitutability for certain categories; a prototype implementation reduces transmission volume by approximately 10% compared to traditional caching. This work presents the first empirical validation of open-source multimodal LLMs for large-scale semantic caching, establishing a novel paradigm for enhancing web affordability and efficiency in resource-constrained environments.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid growth of web content has led to increasingly large webpages, posing significant challenges for Internet affordability, especially in developing countries where data costs remain prohibitively high. We propose semantic caching using Large Language Models (LLMs) to improve web affordability by enabling reuse of semantically similar images within webpages. Analyzing 50 leading news and media websites, encompassing 4,264 images and over 40,000 image pairs, we demonstrate potential for significant data transfer reduction, with some website categories showing up to 37% of images as replaceable. Our proof-of-concept architecture shows users can achieve approximately 10% greater byte savings compared to exact caching. We evaluate both commercial and open-source multi-modal LLMs for assessing semantic replaceability. GPT-4o performs best with a low Normalized Root Mean Square Error of 0.1735 and a weighted F1 score of 0.8374, while the open-source LLaMA 3.1 model shows comparable performance, highlighting its viability for large-scale applications. This approach offers benefits for both users and website operators, substantially reducing data transmission. We discuss ethical concerns and practical challenges, including semantic preservation, user-driven cache configuration, privacy concerns, and potential resistance from website operators

Problem

• Reducing web data costs via semantic image caching
• Evaluating LLMs for image replaceability in webpages
• Addressing ethical and practical caching challenges

Innovation

• Semantic caching using LLMs for web affordability
• Reuse semantically similar images to reduce data
• Multi-modal LLMs assess image replaceability effectively