Browse State-of-the-Art › Source Code Summarization
Source Code Summarization
39 papers with code · 9 benchmarks · 7 datasets archive 2025-07-28
Code Summarization is a task that tries to comprehend code and automatically generate descriptions directly from the source code.
Source: Improving Automatic Source Code Summarization via Deep Reinforcement Learning
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
9 leaderboard tables shown for this task, 9 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
7 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: 58 · with a code link: 39 · where Syntology ran a sample: 6 (6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 58 tagged: 6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 58 of 58, 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.
-
1 May 2020 9 repositories listedGenerating a readable summary that describes the functionality of a program is known as source code summarization.
-
4 Apr 2019 7 repositories listedThe main use for these descriptions is in software documentation e. g. the one-sentence Java method descriptions in JavaDocs.
-
4 Aug 2018 6 repositories listed Syntology community repositories only · 3 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; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval.
-
5 Nov 2018 3 repositories listed Syntology official (archive's flag): 11 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples)Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input.
-
31 Mar 2021 2 repositories listedJupyter notebook allows data scientists to write machine learning code together with its documentation in cells.
-
10 Mar 2021 2 repositories listedExperiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models.
-
6 Apr 2020 2 repositories listedThe first approaches to use structural information flattened the AST into a sequence.
-
14 Oct 2019 2 repositories listed Syntology official (archive's flag): 3 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 4 pointer-only (licence)Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development.
-
17 Nov 2018 2 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major…
-
14 May 2025 1 repository listedRecent advancements in source code summarization have leveraged transformer-based pre-trained models, including Large Language Models of Code (LLMCs), to automate and improve the generation of code summaries.
-
9 Jul 2024 1 repository listedWe hope that our findings can provide a comprehensive understanding of code summarization in the era of LLMs.
-
26 Dec 2023 1 repository listedOur comprehensive experimental results show that PromptCS significantly outperforms instruction prompting schemes (including zero-shot learning and few-shot learning) on all four widely used metrics, and is comparable…
-
5 Sep 2023 1 repository listedSource code summarization is the task of writing natural language descriptions of source code.
-
28 Aug 2023 1 repository listedA code summary is a brief natural language description of source code.
-
14 Aug 2023 1 repository listedThis paper presents a procedure for and evaluation of using a semantic similarity metric as a loss function for neural source code summarization.
-
21 Jul 2023 1 repository listedFor example, by taking the entire subroutine as input to a Transformer or RNN-based encoder.
-
18 May 2023 1 repository listedIn this paper, we propose a fine-grained Token-level retrieval-augmented mechanism (Tram) on the decoder side rather than the encoder side to enhance the performance of neural models and produce more low-frequency…
-
15 Jun 2022 1 repository listedThe extractive module in the framework performs a task of extractive code summarization, which takes in the code snippet and predicts important statements containing key factual details.
-
18 Mar 2022 1 repository listedThey use the learned code representations as input to code summarization models, which can accordingly generate summaries describing source code.
-
14 Feb 2022 1 repository listedWe further show that how the proposed SCRIPT captures the structural relative dependencies.
-
28 Jan 2022 1 repository listedIt is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks.
-
13 Jan 2022 1 repository listedThereby, we propose a flexible and robust approach for automatic code summarization, based on neural models.
-
27 Nov 2021 1 repository listedAutomated source code summarization is a task that generates summarized information about the purpose, usage, and--or implementation of methods and classes to support understanding of these code entities.
-
16 Nov 2021 1 repository listedIn this paper, we propose CODESCRIBE to model the hierarchical syntax structure of code by introducing a novel triplet position for code summarization.
-
4 Nov 2021 1 repository listedSpecifically, we propose to construct graphs for the source code and queries with bidirectional GGNN (BiGGNN) to capture the local structural information of the source code and queries.
-
15 Jul 2021 1 repository listedTo achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code…
-
15 Jun 2021 1 repository listedAutomated source code summarization is a popular software engineering research topic wherein machine translation models are employed to "translate" code snippets into relevant natural language descriptions.
-
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)In this study, we present CoDesc -- a large parallel dataset composed of 4.
-
6 Apr 2021 1 repository listedSimultaneously, the transformer model, especially its combination with transfer learning, has been proven to be a powerful technique for natural language processing tasks.
-
22 Mar 2021 1 repository listedSource code summarization of a subroutine is the task of writing a short, natural language description of that subroutine.
-
21 Mar 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result (of 8 harvested samples)
-
14 Mar 2021 1 repository listed
-
26 Feb 2021 1 repository listed
-
29 Dec 2020 1 repository listed
-
17 Sep 2020 1 repository listed
-
9 Jul 2020 1 repository listed
-
9 Jun 2020 1 repository listed
-
19 Jun 2019 1 repository listed
-
1 Aug 2016 1 repository listed
-
ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization1 Jul 2024 0 repositories listed
-
On Training a Neural Network to Explain Binaries30 Apr 2024 0 repositories listed
-
EditSum: A Retrieve-and-Edit Framework for Source Code Summarization26 Aug 2023 0 repositories listed
-
Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization16 May 2023 0 repositories listed
-
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization1 May 2022 0 repositories listed
-
Meta Learning for Code Summarization20 Jan 2022 0 repositories listed
-
Meta Learning for Code Summarization16 Nov 2021 0 repositories listed
-
Retrieval-based Layer-wise Adaptive Transformer for Source Code Summarization16 Nov 2021 0 repositories listed
-
Learning Sequential and Structural Information for Source Code Summarization1 Aug 2021 0 repositories listed
-
Code Structure Guided Transformer for Source Code Summarization19 Apr 2021 0 repositories listed
-
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach21 Mar 2021 0 repositories listed
-
WheaCha: A Method for Explaining the Predictions of Models of Code9 Feb 2021 0 repositories listed
-
GN-Transformer: Fusing AST and Source Code information in Graph Networks1 Jan 2021 0 repositories listed
-
Automatic Source Code Summarization via Reinforcement Learning14 Dec 2020 0 repositories listed
-
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations6 Sep 2020 0 repositories listed
-
A Structural Transformer with Relative Positions in Trees for Code-to-Sequence Tasks4 Jun 2020 0 repositories listed
-
Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning24 Feb 2020 0 repositories listed
-
A Convolutional Neural Network for Language-Agnostic Source Code Summarization29 Mar 2019 0 repositories listed
-
23 May 2018 0 repositories listed
Syntology lines on 6 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