Impact of Intermediate-Task Training on Cross-Lingual Zero-Shot Performance of Multilingual LLMs

Abstract

Abstract: The use of Large Language Models (LLMs) for program code generation has gained substantial attention, but their biases and limitations with non-English prompts challenge global inclusivity. This paper investigates the complexities of multilingual prompt-based code generation. Our evaluations of LLMs, including CODELLAMA and CODEGEMMA, reveal significant disparities in code quality for non-English prompts; we also demonstrate the inadequacy of simple approaches like prompt translation, bootstrapped data augmentation, and fine-tuning. To address this, we propose a zero-shot cross-lingual approac

Research Question

What is the impact of intermediate-task training using code-related tasks (e.g., code generation, code summarization) on the cross-lingual zero-shot performance of multilingual LLMs, evaluated on benchmarks like MBXP or CodeXGLUE?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance