MAS-LitEval : Multi-Agent System for Literary Translation Quality Assessment

TL;DR

MAS-LitEval is a multi-agent system leveraging Large Language Models to evaluate literary translation quality by capturing cultural, narrative, and stylistic nuances, outperforming traditional metrics.

Contribution

It introduces a novel multi-agent framework using LLMs for nuanced literary translation assessment, addressing limitations of existing lexical overlap metrics.

Findings

MAS-LitEval outperforms traditional metrics in capturing literary nuances.

Top models scored up to 0.890 in evaluation accuracy.

The system provides a scalable and practical tool for translation quality assessment.

Abstract

Literary translation requires preserving cultural nuances and stylistic elements, which traditional metrics like BLEU and METEOR fail to assess due to their focus on lexical overlap. This oversight neglects the narrative consistency and stylistic fidelity that are crucial for literary works. To address this, we propose MAS-LitEval, a multi-agent system using Large Language Models (LLMs) to evaluate translations based on terminology, narrative, and style. We tested MAS-LitEval on translations of The Little Prince and A Connecticut Yankee in King Arthur's Court, generated by various LLMs, and compared it to traditional metrics. \textbf{MAS-LitEval} outperformed these metrics, with top models scoring up to 0.890 in capturing literary nuances. This work introduces a scalable, nuanced framework for Translation Quality Assessment (TQA), offering a practical tool for translators and researchers.