Break-It-Fix-It: Unsupervised Learning for Program Repair

• URL: http://arxiv.org/abs/2106.06600v1
• Date: Fri, 11 Jun 2021 20:31:04 GMT
• Title: Break-It-Fix-It: Unsupervised Learning for Program Repair
• Authors: Michihiro Yasunaga, Percy Liang
• Abstract summary: We propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas. We use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python and 71.7% on DeepFix.
• Score: 90.55497679266442
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with no errors). Existing works create training data consisting of (bad, good) pairs by corrupting good examples using heuristics (e.g., dropping tokens). However, fixers trained on this synthetically-generated data do not extrapolate well to the real distribution of bad inputs. To bridge this gap, we propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas: (i) we use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data, and (ii) we train a breaker to generate realistic bad code from good code. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. We evaluate BIFI on two code repair datasets: GitHub-Python, a new dataset we introduce where the goal is to repair Python code with AST parse errors; and DeepFix, where the goal is to repair C code with compiler errors. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python (+28.5%) and 71.7% on DeepFix (+5.6%). Notably, BIFI does not require any labeled data; we hope it will be a strong starting point for unsupervised learning of various repair tasks.

Related papers

• Leveraging Large Language Models in Code Question Answering: Baselines and Issues [0.1617522438111378]
  This paper presents a work devoted to using large language models for question answering over source code in Python. The proposed method for implementing a source code question answering system involves fine-tuning a large language model on a unified dataset of questions and answers for Python code. We report BLEU-4, BERTScore F1, BLEURT, and Exact Match metric values, along with the conclusions from the manual error analysis.
  arXiv  Detail & Related papers  (2024-11-05T11:25:12Z)
• LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT [28.711745671275477]
  LecPrompt is a prompt-based approach to localize and repair logical errors. It harnesses the capabilities of CodeBERT, a transformer-based large language model trained on code. For Python, LecPrompt achieves a noteworthy 74.58% top-1 token-level repair accuracy. In Java, LecPrompt delivers a 69.23% top-1 token-level repair accuracy.
  arXiv  Detail & Related papers  (2024-10-10T01:56:04Z)
• Fact Checking Beyond Training Set [64.88575826304024]
  We show that the retriever-reader suffers from performance deterioration when it is trained on labeled data from one domain and used in another domain. We propose an adversarial algorithm to make the retriever component robust against distribution shift. We then construct eight fact checking scenarios from these datasets, and compare our model to a set of strong baseline models.
  arXiv  Detail & Related papers  (2024-03-27T15:15:14Z)
• DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models [3.1690235522182104]
  Large language models (LLMs) are increasingly used to solve various programming tasks. We show that the task is difficult as it requires the model to learn long-range code relationships. We propose a technique to address these challenges with a new approach for querying and fine-tuning LLMs.
  arXiv  Detail & Related papers  (2024-02-19T18:35:40Z)
• Bit-flipping Decoder Failure Rate Estimation for (v,w)-regular Codes [84.0257274213152]
  We propose a new technique to provide accurate estimates of the DFR of a two-iterations (parallel) bit flipping decoder. We validate our results, providing comparisons of the modeled and simulated weight of the syndrome, incorrectly-guessed error bit distribution at the end of the first iteration, and two-itcrypteration Decoding Failure Rates (DFR)
  arXiv  Detail & Related papers  (2024-01-30T11:40:24Z)
• RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [75.40584530380589]
  We propose a novel Retrieval-Augmented Patch Generation framework (RAP-Gen) RAP-Gen explicitly leveraging relevant fix patterns retrieved from a list of previous bug-fix pairs. We evaluate RAP-Gen on three benchmarks in two programming languages, including the TFix benchmark in JavaScript, and Code Refinement and Defects4J benchmarks in Java.
  arXiv  Detail & Related papers  (2023-09-12T08:52:56Z)
• Repairing Bugs in Python Assignments Using Large Language Models [9.973714032271708]
  We propose to use a large language model trained on code to build an APR system for programming assignments. Our system can fix both syntactic and semantic mistakes by combining multi-modal prompts, iterative querying, test-case-based selection of few-shots, and program chunking. We evaluate MMAPR on 286 real student programs and compare to a baseline built by combining a state-of-the-art Python syntax repair engine, BIFI, and state-of-the-art Python semantic repair engine for student assignments, Refactory.
  arXiv  Detail & Related papers  (2022-09-29T15:41:17Z)
• Generating Bug-Fixes Using Pretrained Transformers [11.012132897417592]
  We introduce a data-driven program repair approach which learns to detect and fix bugs in Java methods mined from real-world GitHub. We show that pretraining on source code programs improves the number of patches found by 33% as compared to supervised training from scratch. We refine the standard accuracy evaluation metric into non-deletion and deletion-only fixes, and show that our best model generates 75% more non-deletion fixes than the previous state of the art.
  arXiv  Detail & Related papers  (2021-04-16T05:27:04Z)
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights [92.16372657233394]
  Self-supervised learning techniques can boost performance by learning useful representations from unlabelled data. We show that by learning Bayesian instance weights for the unlabelled data, we can improve the downstream classification accuracy. Our method, BetaDataWeighter is evaluated using the popular self-supervised rotation prediction task on STL-10 and Visual Decathlon.
  arXiv  Detail & Related papers  (2020-06-22T15:59:32Z)
• Graph-based, Self-Supervised Program Repair from Diagnostic Feedback [108.48853808418725]
  We introduce a program-feedback graph, which connects symbols relevant to program repair in source code and diagnostic feedback. We then apply a graph neural network on top to model the reasoning process. We present a self-supervised learning paradigm for program repair that leverages unlabeled programs available online.
  arXiv  Detail & Related papers  (2020-05-20T07:24:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.