QoS-QoE Translation with Large Language Model

2026-04-09

AI Summary

This work addresses the challenge of modeling, generalizing, and reusing the relationship between Quality of Service (QoS) metrics and user-perceived Quality of Experience (QoE) in multimedia systems. To this end, we present the first structured, literature-based QoS–QoE relationship dataset, automatically constructed from video streaming studies with contextual metadata. We devise a data curation pipeline encompassing literature screening, relation extraction, and iterative evaluation, and employ it to supervise fine-tune large language models (LLMs) for bidirectional prediction—translating between continuous QoS values and discrete QoE labels, and vice versa. Experimental results demonstrate that the fine-tuned models achieve strong performance on both translation directions. The dataset and code are publicly released, establishing the first LLM benchmark and a reproducible foundation for multimedia quality modeling research.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

QoS-QoE translation is a fundamental problem in multimedia systems because it characterizes how measurable system and network conditions affect user-perceived experience. Although many prior studies have examined this relationship, their findings are often developed for specific setups and remain scattered across papers, experimental settings, and reporting formats, limiting systematic reuse, cross-scenario generalization, and large-scale analysis. To address this gap, we first introduce QoS-QoE Translation dataset, a source-grounded dataset of structured QoS-QoE relationships from the multimedia literature, with a focus on video streaming related tasks. We construct the dataset through an automated pipeline that combines paper curation, QoS-QoE relationship extraction, and iterative data evaluation. Each record preserves the extracted relationship together with parameter definitions, supporting evidence, and contextual metadata. We further evaluate the capability of large language models (LLMs) on QoS-QoE translation, both before and after supervised fine-tuning on our dataset, and show strong performance on both continuous-value and discrete-label prediction in bidirectional translation, from QoS-QoE and QoE-QoS. Our dataset provides a foundation for benchmarking LLMs in QoS-QoE translation and for supporting future LLM-based reasoning for multimedia quality prediction and optimization. The complete dataset and code are publicly available at https://yyu6969.github.io/qos-qoe-translation-page/, for full reproducibility and open access.

Problem

• QoS-QoE translation
• multimedia systems
• user-perceived experience
• systematic reuse
• cross-scenario generalization

Innovation

• QoS-QoE translation
• large language models
• structured dataset
• multimedia quality prediction
• supervised fine-tuning