Browse State-of-the-Art › Code Search
Code Search
60 papers with code · 7 benchmarks · 14 datasets archive 2025-07-28
The goal of Code Search is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
14 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 125 · with a code link: 60 · where Syntology ran a sample: 16 (14 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (16 of 125 tagged: 14 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 125, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
20 Sep 2019 14 repositories listed Syntology official (archive's flag): 3 ran · 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified (of 17 harvested samples) · 2 pointer-only (licence)To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance…
-
9 Feb 2021 7 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Benchmark datasets have a significant impact on accelerating research in programming language tasks.
-
8 Apr 2024 5 repositories listed Syntology official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 1 pointer-only (licence)Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding.
-
28 Aug 2023 2 repositories listedBy leveraging code examples mined from the library source and automatically generated code examples based on the pull requests, we infer transformation rules in \comby, a language for structural code search and replace.
-
31 May 2023 2 repositories listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 4 pointer-only (licence)SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations…
-
13 May 2023 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)To address these limitations, we propose ``CodeT5+'', a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks.
-
8 Mar 2022 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 4 harvested samples)Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task.
-
16 Jun 2021 2 repositories listedThe goal of this paper is to evaluate and compare the extent of memorization and generalization in neural code intelligence models.
-
15 Feb 2021 2 repositories listedRecent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.
-
3 Sep 2020 2 repositories listedWe propose a technique for semantic code search: A Convolutional Neural Network approach to code retrieval (CoNCRA).
-
9 May 2019 2 repositories listedOur evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more…
-
10 Apr 2025 1 repository listedIn this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching.
-
10 Feb 2025 1 repository listedWe define the task of repository-level code search as retrieving the set of files from the current state of a code repository that are most relevant to addressing a user's question or bug.
-
26 Nov 2024 1 repository listedLow isotropy in an embedding space impairs performance on tasks involving semantic inference.
-
21 Nov 2024 1 repository listedThis progress is largely attributed to the development of generalizable source code representations that effectively capture the syntactic and semantic characteristics of code.
-
10 Aug 2024 1 repository listedAssembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs.
-
3 Jul 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval.
-
17 Jun 2024 1 repository listedSemantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering.
-
10 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Recent advances have been improving the context windows of Large Language Models (LLMs).
-
3 May 2024 1 repository listedThe capability of accurately determining code similarity is crucial in many tasks related to software development.
-
25 Mar 2024 1 repository listedRetrieval-based code question answering seeks to match user queries in natural language to relevant code snippets.
-
18 Jan 2024 1 repository listedAssessing similarity in source code has gained significant attention in recent years due to its importance in software engineering tasks such as clone detection and code search and recommendation.
-
9 Jan 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)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…
-
16 Nov 2023 1 repository listedLanguage models can serve as a valuable tool for software developers to increase productivity.
-
10 Nov 2023 1 repository listedOur framework has several advantages over existing methods: (1) It is flexible and adaptable, because it can easily be extended to other downstream tasks that require code representation (such as code-clone detection…
-
12 Oct 2023 1 repository listedAs such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.
-
12 Oct 2023 1 repository listedIn our proposed loss function, we apply three methods to estimate the weights of negative pairs and show that the vanilla InfoNCE loss is a special case of Soft-InfoNCE.
-
27 Jun 2023 1 repository listedCode search is a task to find programming codes that semantically match the given natural language queries.
-
27 May 2023 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 14 harvested samples)Neural code search models are hence behind many such engines.
-
9 May 2023 1 repository listedWe present The Vault, a dataset of high-quality code-text pairs in multiple programming languages for training large language models to understand and generate code.
-
8 May 2023 1 repository listed
-
5 May 2023 1 repository listed
-
28 Mar 2023 1 repository listed
-
23 Oct 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
21 Oct 2022 1 repository listed
-
16 Jun 2022 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 2 pointer-only (licence)
-
21 May 2022 1 repository listed
-
16 Feb 2022 1 repository listed
-
14 Feb 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
14 Feb 2022 1 repository listed
-
27 Jan 2022 1 repository listed
-
26 Jan 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
24 Jan 2022 1 repository listed
-
24 Jan 2022 1 repository listed
-
4 Dec 2021 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 13 harvested samples)
-
4 Nov 2021 1 repository listed
-
10 Jul 2021 1 repository listed
-
2 Jul 2021 1 repository listed
-
29 May 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
27 May 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
24 Mar 2021 1 repository listed
-
21 Jan 2021 1 repository listed
-
24 Nov 2020 1 repository listed
-
17 Sep 2020 1 repository listed
-
27 Aug 2020 1 repository listed
-
16 Aug 2020 1 repository listed
-
26 Jul 2020 1 repository listed
-
21 Feb 2020 1 repository listed
-
22 Mar 2018 1 repository listed
-
MGS3: A Multi-Granularity Self-Supervised Code Search Framework30 May 2025 0 repositories listed
-
DeepRTL2: A Versatile Model for RTL-Related Tasks28 May 2025 0 repositories listed
-
Knowledge Graph Based Repository-Level Code Generation20 May 2025 0 repositories listed
-
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models20 May 2025 0 repositories listed
-
Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks28 Apr 2025 0 repositories listed
-
Towards Leveraging Large Language Model Summaries for Topic Modeling in Source Code24 Apr 2025 0 repositories listed
-
A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection22 Apr 2025 0 repositories listed
-
11 Mar 2025 0 repositories listed Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
LoRACode: LoRA Adapters for Code Embeddings7 Mar 2025 0 repositories listed
-
MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings4 Mar 2025 0 repositories listed
-
Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets27 Feb 2025 0 repositories listed
-
URECA: The Chain of Two Minimum Set Cover Problems exists behind Adaptation to Shifts in Semantic Code Search11 Feb 2025 0 repositories listed
-
OrcaLoca: An LLM Agent Framework for Software Issue Localization1 Feb 2025 0 repositories listed
-
On the Compression of Language Models for Code: An Empirical Study on CodeBERT18 Dec 2024 0 repositories listed
-
In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics7 Oct 2024 0 repositories listed
-
Deep Code Search with Naming-Agnostic Contrastive Multi-View Learning18 Aug 2024 0 repositories listed
-
Natural Language Outlines for Code: Literate Programming in the LLM Era9 Aug 2024 0 repositories listed
-
SpecRover: Code Intent Extraction via LLMs5 Aug 2024 0 repositories listed
-
LLM Agents Improve Semantic Code Search5 Aug 2024 0 repositories listed
-
Toward Exploring the Code Understanding Capabilities of Pre-trained Code Generation Models18 Jun 2024 0 repositories listed
-
Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance25 Nov 2023 0 repositories listed
-
Noisy Pair Corrector for Dense Retrieval7 Nov 2023 0 repositories listed
-
ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models15 Oct 2023 0 repositories listed
-
Contrastive Prompt Learning-based Code Search based on Interaction Matrix10 Oct 2023 0 repositories listed
-
Code Representation Pre-training with Complements from Program Executions4 Sep 2023 0 repositories listed
-
Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion1 Sep 2023 0 repositories listed
-
Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark9 Aug 2023 0 repositories listed
-
CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search19 May 2023 0 repositories listed
-
Searching by Code: a New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets19 May 2023 0 repositories listed
-
Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation26 Apr 2023 0 repositories listed
-
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities20 Dec 2022 0 repositories listed
-
You Don't Know Search: Helping Users Find Code by Automatically Evaluating Alternative Queries7 Dec 2022 0 repositories listed
-
CodeDSI: Differentiable Code Search1 Oct 2022 0 repositories listed
-
CSSAM:Code Search via Attention Matching of Code Semantics and Structures8 Aug 2022 0 repositories listed
-
CoCoSoDa: Effective Contrastive Learning for Code Search7 Apr 2022 0 repositories listed
-
On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages5 Apr 2022 0 repositories listed
-
Accelerating Code Search with Deep Hashing and Code Classification29 Mar 2022 0 repositories listed
-
AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees20 Jan 2022 0 repositories listed
-
Analyzing CodeBERT's Performance on Natural Language Code Search16 Jan 2022 0 repositories listed
-
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning10 Jan 2022 0 repositories listed
Syntology lines on 19 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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