# Rethinking Pivot Programming Languages in Code Language Models

arXiv: https://arxiv.org/abs/2609.22988 · HTML: https://mlsanity.com/paper/2609.22988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Placed in

- LLM reasoning

## Builds on (most cited first, 7 of 7)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?](https://mlsanity.com/paper/2512.19980/) (2025)
- [Beyond Language Boundaries: Uncovering Programming Language Families for Code Language Models](https://mlsanity.com/paper/2512.19509/) (2025)
- [Large Language Models for Multilingual Code Intelligence: A Survey](https://mlsanity.com/paper/2604.25960/) (2026)
- [Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models](https://mlsanity.com/paper/2505.16385/) (2025)

## Abstract (arXiv)

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.