QoS-QoE Translation with Large Language Model

TL;DR

This paper introduces a new dataset and evaluates large language models on translating Quality of Service to Quality of Experience in multimedia, enabling better understanding and prediction of user experience based on system metrics.

Contribution

The paper creates a structured QoS-QoE dataset from literature and assesses LLMs' ability to perform bidirectional translation, enhancing multimedia quality prediction.

Findings

LLMs show strong performance in QoS-QoE translation tasks.

Supervised fine-tuning improves LLM accuracy in both directions.

The dataset supports benchmarking and future research in multimedia quality modeling.

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.