Program Repair

33 papers with code • 3 benchmarks • 8 datasets

Task of teaching ML models to modify an existing program to fix a bug in a given code.

Evaluating Program Repair with Semantic-Preserving Transformations: A Naturalness Assessment

thanhlecongg/naturaltransformationforbenchmarkingnpr 19 Feb 2024

In this paper, we investigate the naturalness of semantic-preserving transformations and their impacts on the evaluation of NPR.

1
19 Feb 2024

RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair

assert-kth/repairllama 25 Dec 2023

This results in RepairLLaMA producing a highly effective `program repair adapter' for fixing bugs with language models.

13
25 Dec 2023

Breaking the Silence: the Threats of Using LLMs in Software Engineering

llm4se/obfuscated-chatgpt-experiments 13 Dec 2023

Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization.

1
13 Dec 2023

Out of Context: How important is Local Context in Neural Program Repair?

giganticode/out_of_context_paper_data 8 Dec 2023

Our results indicate that overall repair success increases with the size of the local context (albeit not for all bug types) and confirm the common practice that roughly 50-60% of the input window should be used for context leading the bug.

1
08 Dec 2023

Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair

ise-uiuc/Repilot 1 Sep 2023

Therefore, we propose Repilot, a general code generation framework to further copilot the AI "copilots" (i. e., LLMs) by synthesizing more valid patches during the repair process.

118
01 Sep 2023

Graph Neural Networks For Mapping Variables Between Programs -- Extended Version

pmorvalho/ecai23-gnns-for-mapping-variables-between-programs 24 Jul 2023

Typically, in order to compare two programs, a relation between both programs' sets of variables is required.

0
24 Jul 2023

How Effective Are Neural Networks for Fixing Security Vulnerabilities

lin-tan/llm-vul 29 May 2023

The results call for innovations to enhance automated Java vulnerability repair such as creating larger vulnerability repair training data, tuning LLMs with such data, and applying code simplification transformation to facilitate vulnerability repair.

14
29 May 2023

xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval

ntunlp/xCodeEval 6 Mar 2023

Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.

56
06 Mar 2023

KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair

lin-tan/knod 3 Feb 2023

KNOD has two major novelties, including (1) a novel three-stage tree decoder, which directly generates Abstract Syntax Trees of patched code according to the inherent tree structure, and (2) a novel domain-rule distillation, which leverages syntactic and semantic rules and teacher-student distributions to explicitly inject the domain knowledge into the decoding procedure during both the training and inference phases.

29
03 Feb 2023

Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning

thanhlecongg/Invalidator 3 Jan 2023

In case our approach fails to determine an overfitting patch based on invariants, INVALIDATOR utilizes a trained model from labeled patches to assess patch correctness based on program syntax.

6
03 Jan 2023