MATCH: Task-Driven Code Evaluation through Contrastive Learning

• URL: http://arxiv.org/abs/2510.23169v2
• Date: Tue, 28 Oct 2025 07:44:06 GMT
• Title: MATCH: Task-Driven Code Evaluation through Contrastive Learning
• Authors: Marah Ghoummaid, Vladimir Tchuiev, Ofek Glick, Michal Moshkovitz, Dotan Di Castro,
• Abstract summary: GitHub Copilot estimated to generate 46% of the code on GitHub.<n>Traditional evaluation methods, such as unit tests, are often unscalable and costly.<n>This paper introduces MATCH, a novel reference-free metric.
• Score: 11.156827035309407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-based code generation is increasingly prevalent, with GitHub Copilot estimated to generate 46% of the code on GitHub. Accurately evaluating how well generated code aligns with developer intent remains a critical challenge. Traditional evaluation methods, such as unit tests, are often unscalable and costly. Syntactic similarity metrics (e.g., BLEU, ROUGE) fail to capture code functionality, and metrics like CodeBERTScore require reference code, which is not always available. To address the gap in reference-free evaluation, with few alternatives such as ICE-Score, this paper introduces MATCH, a novel reference-free metric. MATCH uses Contrastive Learning to generate meaningful embeddings for code and natural language task descriptions, enabling similarity scoring that reflects how well generated code implements the task. We show that MATCH achieves stronger correlations with functional correctness and human preference than existing metrics across multiple programming languages.

Related papers

• Is Compression Really Linear with Code Intelligence? [60.123628177110206]
  textitFormat Annealing is a lightweight, transparent training methodology designed to assess the intrinsic capabilities of pre-trained models equitably.<n>Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and bits-per-character (BPC)<n>Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.
  arXiv  Detail & Related papers  (2025-05-16T16:59:14Z)
• Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates [46.74037090843497]
  Large Language Models (LLMs) are transforming the way developers approach programming by automatically generating code based on natural language descriptions. This paper puts forward RankEF, an innovative approach for code ranking that leverages execution feedback. Experiments on three code generation benchmarks demonstrate that RankEF significantly outperforms the state-of-the-art CodeRanker.
  arXiv  Detail & Related papers  (2024-08-26T01:48:57Z)
• CodeScore-R: An Automated Robustness Metric for Assessing the FunctionalCorrectness of Code Synthesis [17.747095451792084]
  We propose an automated robust metric, called CodeScore-R, for evaluating the functionality of code synthesis. In the tasks of code generation and migration in Java and Python, CodeScore-R outperforms other metrics.
  arXiv  Detail & Related papers  (2024-06-11T02:51:17Z)
• On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation [4.065344017083881]
  We analyze the ability of embedding-based metrics like CodeBERTScore to measure functional correctness and other helpful constructs like editing effort. Our results show that while they have a weak correlation with functional correctness (0.16), they are strongly correlated (0.72) with editing effort.
  arXiv  Detail & Related papers  (2024-04-26T15:54:39Z)
• Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective [85.48043537327258]
  We propose MANGO (comMents As Natural loGic pivOts), including a comment contrastive training strategy and a corresponding logical comment decoding strategy. Results indicate that MANGO significantly improves the code pass rate based on the strong baselines. The robustness of the logical comment decoding strategy is notably higher than the Chain-of-thoughts prompting.
  arXiv  Detail & Related papers  (2024-04-11T08:30:46Z)
• Leveraging Generative AI: Improving Software Metadata Classification with Generated Code-Comment Pairs [0.0]
  In software development, code comments play a crucial role in enhancing code comprehension and collaboration. This research paper addresses the challenge of objectively classifying code comments as "Useful" or "Not Useful" We propose a novel solution that harnesses contextualized embeddings, particularly BERT, to automate this classification process.
  arXiv  Detail & Related papers  (2023-10-14T12:09:43Z)
• InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback [50.725076393314964]
  We introduce InterCode, a lightweight, flexible, and easy-to-use framework of interactive coding as a standard reinforcement learning environment. Our framework is language and platform agnostic, uses self-contained Docker environments to provide safe and reproducible execution. We demonstrate InterCode's viability as a testbed by evaluating multiple state-of-the-art LLMs configured with different prompting strategies.
  arXiv  Detail & Related papers  (2023-06-26T17:59:50Z)
• CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code [75.08995072899594]
  We propose CodeBERTScore: an evaluation metric for code generation. CodeBERTScore encodes the natural language input preceding the generated code. We find that CodeBERTScore achieves a higher correlation with human preference and with functional correctness than all existing metrics.
  arXiv  Detail & Related papers  (2023-02-10T22:12:05Z)
• Interactive Code Generation via Test-Driven User-Intent Formalization [60.90035204567797]
  Large language models (LLMs) produce code from informal natural language (NL) intent. It is hard to define a notion of correctness since natural language can be ambiguous and lacks a formal semantics. We describe a language-agnostic abstract algorithm and a concrete implementation TiCoder.
  arXiv  Detail & Related papers  (2022-08-11T17:41:08Z)
• ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
  We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
  arXiv  Detail & Related papers  (2022-03-15T08:25:08Z)
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis [57.87741831987889]
  In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy. We introduce a new automatic evaluation metric, dubbed CodeBLEU. It absorbs the strength of BLEU in the n-gram match and further injects code syntax via abstract syntax trees (AST) and code semantics via data-flow.
  arXiv  Detail & Related papers  (2020-09-22T03:10:49Z)

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.