Papers › Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search

Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search

9 Jan 2024arXiv:2401.04514archive 2025-07-28

Haochen Li, Xin Zhou, Zhiqi Shen

In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the principal challenge of modality misalignment between code snippets and natural language queries, particularly with the demonstrated code generation capabilities of Large Language Models (LLMs). Nevertheless, our preliminary investigations indicate that the improvements conferred by such an LLM-augmented framework are somewhat constrained. This limitation could potentially be ascribed to the fact that the generated codes, albeit functionally accurate, frequently display a pronounced stylistic deviation from the ground truth code in the codebase. In this paper, we extend the foundational GAR framework and propose a simple yet effective method that additionally Rewrites the Code (ReCo) within the codebase for style normalization. Experimental results demonstrate that ReCo significantly boosts retrieval accuracy across sparse (up to 35.7%), zero-shot dense (up to 27.6%), and fine-tuned dense (up to 23.6%) retrieval settings in diverse search scenarios. To further elucidate the advantages of ReCo and stimulate research in code style normalization, we introduce Code Style Similarity, the first metric tailored to quantify stylistic similarities in code. Notably, our empirical findings reveal the inadequacy of existing metrics in capturing stylistic nuances. The source code and data are available at \url{https://github.com/Alex-HaochenLi/ReCo}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.04514")

Code

Syntology Ran 5 of 9 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alex-haochenli/reco officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 5 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
4unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from alex-haochenli/reco. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DFG_csharp alex-haochenli/reco/metrics/parser/DFG.py official repository ran no licence file found · pointer only · ec263cd21fc00661 · report
calc_score alex-haochenli/reco/metrics/rouge.py official repository ran no licence file found · pointer only · ee6b82869d67c8a7 · report
extract_subtrees alex-haochenli/reco/metrics/code_style_sim.py official repository ran no licence file found · pointer only · 8cc674de4fd3c826 · report
my_lcs alex-haochenli/reco/metrics/rouge.py official repository ran no licence file found · pointer only · d6f215d655a876ee · report
pad_sequence alex-haochenli/reco/metrics/utils.py official repository ran no licence file found · pointer only · cd90fe437a24c233 · report
DFG_java alex-haochenli/reco/metrics/parser/DFG.py official repository unverified no licence file found · pointer only · 8ad8aef57770407f · report
DFG_python alex-haochenli/reco/metrics/parser/DFG.py official repository unverified no licence file found · pointer only · e9c213ae4e45bf1b · report
collect_corpus alex-haochenli/reco/ReCo/prepare_bm25_data.py official repository unverified no licence file found · pointer only · eb0d2a3d9e5a7c18 · report
collect_query Alex-HaochenLi/ReCo/ReCo/bm25.py official repository unverified no licence file found · pointer only · fe4aede7dc3dd319 · report

Tasks

Code GenerationCode SearchLanguage ModelingLanguage ModellingLarge Language ModelNatural Language QueriesRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections