# Do not copy and paste! Rewriting strategies for code retrieval

arXiv: https://arxiv.org/abs/2605.08299 · HTML: https://mlsanity.com/paper/2605.08299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 12 of 12)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval](https://mlsanity.com/paper/2411.12644/) (2024)
- [Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search](https://mlsanity.com/paper/2401.04514/) (2024)
- [MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings](https://mlsanity.com/paper/2503.03008/) (2025)
- [Assessing Code Understanding in LLMs](https://mlsanity.com/paper/2504.00065/) (2025)
- [PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval](https://mlsanity.com/paper/2509.20881/) (2025)

## Abstract (arXiv)

Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and corpora into a normalized style, but leaves two questions open: how much representational shift helps, and when is the per-query LLM call justified? We study a hierarchy of three rewriting strategies: stylistic rephrasing, NL-enriched PseudoCode, and full Natural-Language transcription, under joint query-corpus (QC, online) and corpus-only (C, offline) augmentation, across six CoIR benchmarks, five encoders, and three rewriters spanning independent model families (Qwen, DeepSeek, Mistral). We are the first to evaluate NL-enriched PseudoCode and snippet-level Natural Language as direct retrieval representations, rather than as transient intermediates. Full NL rewriting with QC yields the largest gains (+0.51 absolute NDCG@10 on CT-Contest for MoSE-18), while corpus-only rewriting degrades retrieval in 56 of 90 configurations, about 62%. We introduce two diagnostics, Delta H, token entropy, and Delta s, embedding cosine, and show that Delta H predicts retrieval gain under QC across all three rewriter families: pooled Spearman rho = +0.436, p < 0.001 on DeepSeek+Codestral; rho = +0.593 on Codestral alone; rho = +0.356 on Qwen. This establishes Delta H as a cheap, rewriter-agnostic proxy for deciding when rewriting pays off before running retrieval. Our analysis reframes LLM rewriting as a cost-benefit decision: it is most effective as a remediation layer for lightweight encoders on code-dominant queries, with diminishing returns for strong encoders or NL-heavy queries.