Rethinking Pivot Programming Languages in Code Language Models

2026-09-19

AI Summary

研究重新审视编程语言在代码模型中的中心位置问题，通过控制表示各向异性和长度变化，采用三种视角分析，发现Python更适合英语对齐而非作为通用中心。

Abstract

Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains contested: geometric analyses point to C-family languages and Go, while behavioral evidence highlights Python. We revisit this question under controls for representational anisotropy and length variation across PLs, two confounds that compromise prior cosine-based analyses. Across three code models on multilingual competitive-programming data, we study three views of cross-PL organization: pairwise PL geometry, PL-English alignment, and pivoted retrieval through candidate PL representation spaces. The results are relation-dependent. Code-code geometry reveals structured language regions but no universal center; code-English alignment favors high-level scripting languages; and pivoted retrieval favors different intermediate spaces for code-to-code and English-to-code transfer. These findings suggest that Python's special role is better understood as English-facing affinity than as universal geometric centrality.

Problem

• Pivot Programming Languages
• Code Language Models
• Multilingual
• Geometric Centrality
• English-facing Affinity

Innovation

• representational anisotropy
• length variation
• code-English alignment
• pivoted retrieval