# Revisiting the Role of Natural Language Code Comments in Code Translation

arXiv: https://arxiv.org/abs/2601.16661 · HTML: https://mlsanity.com/paper/2601.16661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [DOBF: A Deobfuscation Pre-Training Objective for Programming Languages](https://mlsanity.com/paper/2102.07492/) (2021)
- [AVATAR: A Parallel Corpus for Java-Python Program Translation](https://mlsanity.com/paper/2108.11590/) (2021)
- [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [Towards Translating Real-World Code with LLMs: A Study of Translating to Rust](https://mlsanity.com/paper/2405.11514/) (2024)
- [Code Structure Guided Transformer for Source Code Summarization](https://mlsanity.com/paper/2104.09340/) (2021)
- [AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation](https://mlsanity.com/paper/2410.24117/) (2024)
- [CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution](https://mlsanity.com/paper/2306.06755/) (2023)
- [Rectifier: Code Translation with Corrector via LLMs](https://mlsanity.com/paper/2407.07472/) (2024)
- [Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?](https://mlsanity.com/paper/2410.09812/) (2024)
- [InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation](https://mlsanity.com/paper/2411.01063/) (2024)
- [Source Code Summarization with Structural Relative Position Guided Transformer](https://mlsanity.com/paper/2202.06521/) (2022)
- [M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization](https://mlsanity.com/paper/2203.09707/) (2022)
- [Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2205.11116/) (2022)
- [Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations](https://mlsanity.com/paper/2311.07070/) (2023)
- [ClassEval-T: Evaluating Large Language Models in Class-Level Code Translation](https://mlsanity.com/paper/2411.06145/) (2024)
- [Specification-Driven Code Translation Powered by Large Language Models: How Far Are We?](https://mlsanity.com/paper/2412.04590/) (2024)
- [Collaboration is all you need: LLM Assisted Safe Code Translation](https://mlsanity.com/paper/2503.11237/) (2025)

## Abstract (arXiv)

The advent of large language models (LLMs) has ushered in a new era in automated code translation across programming languages. Since most code-specific LLMs are pretrained on well-commented code from large repositories like GitHub, it is reasonable to hypothesize that natural language code comments could aid in improving translation quality. Despite their potential relevance, comments are largely absent from existing code translation benchmarks, rendering their impact on translation quality inadequately characterised. In this paper, we present a large-scale empirical study evaluating the impact of comments on translation performance. Our analysis involves more than 80,000 translations, with and without comments, of 1100+ code samples from two distinct benchmarks covering pairwise translations between five different programming languages: C, C++, Go, Java, and Python. Our results provide strong evidence that code comments, particularly those that describe the overall purpose of the code rather than line-by-line functionality, significantly enhance translation accuracy. Based on these findings, we propose COMMENTRA, a code translation approach, and demonstrate that it can potentially double the performance of LLM-based code translation. To the best of our knowledge, our study is the first in terms of its comprehensiveness, scale, and language coverage on how to improve code translation accuracy using code comments.