Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs

TL;DR

This paper introduces the CIA Suite, a framework for evaluating multilingual LLMs using a new test set and a cross-lingual evaluation model, Hercule, which aligns well with human judgments across multiple languages.

Contribution

The paper presents Hercule, a novel cross-lingual evaluation model, and the Recon test set, enabling scalable, accurate multilingual LLM assessment and benchmarking.

Findings

Hercule outperforms proprietary models in aligning with human judgments.

Hercule is effective in zero-shot evaluation for unseen languages.

The CIA Suite facilitates comprehensive multilingual LLM benchmarking.

Abstract

Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on English, revealing a significant gap in multilingual evaluation frameworks. We introduce the Cross Lingual Auto Evaluation (CIA) Suite, an extensible framework that includes evaluator LLMs (Hercule) and a novel test set (Recon) specifically designed for multilingual evaluation. Our test set features 500 human-annotated instructions spanning various task capabilities along with human judgment scores across six languages. This would enable benchmarking of general-purpose multilingual LLMs and facilitate meta-evaluation of Evaluator LLMs. The proposed model, Hercule, is a cross-lingual evaluation model that addresses the scarcity of reference answers in the target language by learning to assign scores to responses based on easily available reference answers in English. Our experiments demonstrate that Hercule aligns more closely with human judgments compared to proprietary models, demonstrating the effectiveness of such cross-lingual evaluation in low resource scenarios. Further, it is also effective in zero-shot evaluation on unseen languages. This study is the first comprehensive examination of cross-lingual evaluation using LLMs, presenting a scalable and effective approach for multilingual assessment. All code, datasets, and models will be publicly available to enable further research in this important area.