# Can LLMs Replace Humans During Code Chunking?

arXiv: https://arxiv.org/abs/2506.19897 · HTML: https://mlsanity.com/paper/2506.19897/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems](https://mlsanity.com/paper/2407.01370/) (2024)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [LumberChunker: Long-Form Narrative Document Segmentation](https://mlsanity.com/paper/2406.17526/) (2024)
- [Towards Translating Real-World Code with LLMs: A Study of Translating to Rust](https://mlsanity.com/paper/2405.11514/) (2024)
- [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://mlsanity.com/paper/2401.07883/) (2024)
- [Grounding Language Model with Chunking-Free In-Context Retrieval](https://mlsanity.com/paper/2402.09760/) (2024)
- [Extending LLMs' Context Window with 100 Samples](https://mlsanity.com/paper/2401.07004/) (2024)
- [An Empirical Study on the Code Refactoring Capability of Large Language Models](https://mlsanity.com/paper/2411.02320/) (2024)
- [From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries](https://mlsanity.com/paper/2406.12824/) (2024)
- [Python Symbolic Execution with LLM-powered Code Generation](https://mlsanity.com/paper/2409.09271/) (2024)
- [Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation](https://mlsanity.com/paper/2407.05437/) (2024)
- [Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation](https://mlsanity.com/paper/2411.14971/) (2024)
- [Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering](https://mlsanity.com/paper/2411.15501/) (2024)
- [Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm](https://mlsanity.com/paper/2408.11198/) (2024)

## Built on by (most cited first, 2 of 2)

- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [SemChunk-C: Semantic Segmentation for C Code](https://mlsanity.com/paper/2606.23697/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have become essential tools in computer science, especially for tasks involving code understanding and generation. However, existing work does not address many of the unique challenges presented by code written for government applications. In particular, government enterprise software is often written in legacy languages like MUMPS or assembly language code (ALC) and the overall token lengths of these systems exceed the context window size for current commercially available LLMs. Additionally, LLMs are primarily trained on modern software languages and have undergone limited testing with legacy languages, making their ability to understand legacy languages unknown and, hence, an area for empirical study. This paper examines the application of LLMs in the modernization of legacy government code written in ALC and MUMPS, addressing the challenges of input limitations. We investigate various code-chunking methods to optimize the generation of summary module comments for legacy code files, evaluating the impact of code-chunking methods on the quality of documentation produced by different LLMs, including GPT-4o, Claude 3 Sonnet, Mixtral, and Llama 3. Our results indicate that LLMs can select partition points closely aligned with human expert partitioning. We also find that chunking approaches have significant impact on downstream tasks such as documentation generation. LLM-created partitions produce comments that are up to 20% more factual and up to 10% more useful than when humans create partitions. Therefore, we conclude that LLMs can be used as suitable replacements for human partitioning of large codebases during LLM-aided modernization.