ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair

• URL: http://arxiv.org/abs/2602.07561v1
• Date: Sat, 07 Feb 2026 14:17:21 GMT
• Title: ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair
• Authors: Quanjun Zhang, Ye Shang, Haichuan Hu, Chunrong Fang, Zhenyu Chen, Liang Xiao,
• Abstract summary: We present ComPass, a pre-trained language model (PLM)-based automated patch correctness assessment approach.<n>We show that ComPass achieves an accuracy of 88.35%, significantly outperforming state-of-the-art baseline APPT.
• Score: 20.606877071567958
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated program repair (APR) attempts to reduce manual debugging efforts and plays a vital role in software maintenance. Despite remarkable progress, APR is still limited in generating overfitting patches, i.e., patches passing available test suites but incorrect. This issue, known as patch overfitting, has become a key concern in the APR community, with numerous approaches proposed to address it. Very recent work proposes a pre-trained language model (PLM)-based automated patch correctness assessment (APCA) approach, indicating the potential of such PLMs in reasoning about patch correctness. Despite being promising, it is still far from perfect due to various limitations, such as the training paradigm and training dataset. In this paper, we present ComPass, a PLM-based APCA approach that leverages contrastive learning and data augmentation to address the technical limitations of prior work. Our work is inspired by the opportunity to integrate contrastive learning with recent PLMs in the field of patch correctness assessment, where large-scale labeled patches are difficult to obtain. ComPass utilizes code transformation rules to generate semantic-preserving code snippets for both unlabeled pre-training corpus and labeled fine-tuning patches. ComPass then pre-trains PLMs with contrastive learning, which captures code features with the same semantics but different structures. ComPass finally integrates representation embeddings of patch code snippets and fine-tunes PLMs with a binary classifier jointly to assess patch code correctness. Experimental results on 2274 real-world patches from Defects4J demonstrate that ComPass achieves an accuracy of 88.35%, significantly outperforming state-of-the-art baseline APPT.

Related papers

• GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning [51.79350934271497]
  GateRA is a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates.<n>By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation.<n> Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods.
  arXiv  Detail & Related papers  (2025-11-15T17:55:47Z)
• RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment [0.0]
  We introduce RePaCA, a novel static APCA technique that leverages Large Language Models (LLMs) specialized in thinking tasks.<n>Our approach achieves state-of-the-art performance, with 83.1% accuracy and an 84.8% F1-score.
  arXiv  Detail & Related papers  (2025-07-30T11:21:09Z)
• Test-Time Adaptation with Binary Feedback [50.20923012663613]
  BiTTA is a novel dual-path optimization framework that balances binary feedback-guided adaptation on uncertain samples with agreement-based self-adaptation on confident predictions.<n> Experiments show BiTTA achieves 13.3%p accuracy improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-05-24T05:24:10Z)
• Parameter-Efficient Fine-Tuning with Attributed Patch Semantic Graph for Automated Patch Correctness Assessment [8.028183762381474]
  Automated program repair (APR) aims to automatically repair program errors without human intervention.<n>Many research efforts have been devoted for automated patch correctness assessment ( APCA)
  arXiv  Detail & Related papers  (2025-05-05T13:15:53Z)
• Teaching Your Models to Understand Code via Focal Preference Alignment [70.71693365502212]
  In existing approaches, a set of n candidate solutions is evaluated based on test case success rates.<n>Because this approach aligns entire failing code blocks rather than pinpointing specific errors, it lacks the granularity necessary to capture meaningful error-correction relationships.<n>We propose Target-DPO, a new preference alignment framework that mimics human iterative debug to refine Code LLMs.
  arXiv  Detail & Related papers  (2025-03-04T16:56:34Z)
• Beyond Next Token Prediction: Patch-Level Training for Large Language Models [69.67438563485887]
  We introduce patch-level training for Large Language Models (LLMs)<n>During patch-level training, we feed the language model shorter sequences of patches and train it to predict the next patch.<n>We show that patch-level training can reduce the overall training costs to 0.5$times$, without compromising the model performance.
  arXiv  Detail & Related papers  (2024-07-17T15:48:39Z)
• 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)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [55.12082817901671]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT)<n>MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies.<n>Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)
• PatchZero: Zero-Shot Automatic Patch Correctness Assessment [13.19425284402493]
  We propose toolname, the patch correctness assessment by adopting a large language model for code. toolname prioritizes labeled patches from existing APR tools that exhibit semantic similarity to those generated by new APR tools. Our experimental results showed that toolname can achieve an accuracy of 84.4% and an F1-score of 86.5% on average.
  arXiv  Detail & Related papers  (2023-03-01T03:12:11Z)
• APPT: Boosting Automated Patch Correctness Prediction via Fine-tuning Pre-trained Models [15.179895484968476]
  We propose APPT, a pre-trained model-based automated patch correctness assessment technique by both pre-training and fine-tuning. We conduct an experiment on 1,183 Defects4J patches and the experimental results show that APPT achieves prediction accuracy of 79.7% and recall of 83.2%.
  arXiv  Detail & Related papers  (2023-01-29T14:28:26Z)
• Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning [6.269370220586248]
  In this paper, we propose a novel technique to automatically assess the correctness of APR-generated patches via semantic and syntactic reasoning. We have conducted experiments on a dataset of 885 patches generated on real-world programs in Defects4J. Experiment results show that INVALIDATOR correctly classified 79% overfitting patches, accounting for 23% more overfitting patches being detected by the best baseline.
  arXiv  Detail & Related papers  (2023-01-03T14:16:32Z)
• DPT: Deformable Patch-based Transformer for Visual Recognition [57.548916081146814]
  We propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way. The DePatch module can work as a plug-and-play module, which can easily be incorporated into different transformers to achieve an end-to-end training.
  arXiv  Detail & Related papers  (2021-07-30T07:33:17Z)

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.