Saved in:
Bibliographic Details
Main Authors: Sheth, Ivaxi, Jonke, Zeno, Mantrach, Amin, Mansour, Saab
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911529114271744
author Sheth, Ivaxi
Jonke, Zeno
Mantrach, Amin
Mansour, Saab
author_facet Sheth, Ivaxi
Jonke, Zeno
Mantrach, Amin
Mansour, Saab
contents As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18557
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
Sheth, Ivaxi
Jonke, Zeno
Mantrach, Amin
Mansour, Saab
Computation and Language
As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.
title Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
topic Computation and Language
url https://arxiv.org/abs/2603.18557