mlsanityData to 14 Oct 2026

Syntax-Guided Program Reduction for Understanding Neural Code Intelligence Models

arXiv 2205.14374 ↗First posted 28 May 2022cs.SE cs.LG cs.PLcited by 7

Not on the map. Why?

Abstract (arXiv)

Neural code intelligence (CI) models are opaque black-boxes and offer little insight on the features they use in making predictions. This opacity may lead to distrust in their prediction and hamper their wider adoption in safety-critical applications. Recently, input program reduction techniques have been proposed to identify key features in the input programs to improve the transparency of CI models. However, this approach is syntax-unaware and does not consider the grammar of the programming language. In this paper, we apply a syntax-guided program reduction technique that considers the grammar of the input programs during reduction. Our experiments on multiple models across different types of input programs show that the syntax-guided program reduction technique is faster and provides smaller sets of key tokens in reduced programs. We also show that the key tokens could be used in generating adversarial examples for up to 65% of the input programs.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

18 of 29 references.

References · 18

  1. 2018code2vec: Learning Distributed Representations of Codecited by 250
  2. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 221
  3. 2017Learning to Represent Programs with Graphscited by 220
  4. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 179
  5. 2018The Adverse Effects of Code Duplication in Machine Learning Models of Codecited by 126
  6. 2016A Convolutional Attention Network for Extreme Summarization of Source Codecited by 91
  7. 2019Adversarial Examples for Models of Codecited by 63
  8. 2020On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformationscited by 44
  9. 2014Learning Natural Coding Conventionscited by 29
  10. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 24
  11. 2021Understanding Neural Code Intelligence Through Program Simplificationcited by 22
  12. 2021Memorization and Generalization in Neural Code Intelligence Modelscited by 19
6 more
  1. 2019A Literature Study of Embeddings on Source Codecited by 18
  2. 2020Probing Model Signal-Awareness via Prediction-Preserving Input Minimizationcited by 14
  3. 2020Embedding Java Classes with code2vec: Improvements from Variable Obfuscationcited by 12
  4. 2020Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformationscited by 9
  5. 2020Towards Demystifying Dimensions of Source Code Embeddingscited by 9
  6. 2021Code2Snapshot: Using Code Snapshots for Learning Representations of Source Codecited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 3.

7 papers.

  1. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 48
  2. 2025The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budgetcited by 12
  3. 2024A Critical Study of What Code-LLMs (Do Not) Learncited by 4
  4. 2023Study of Distractors in Neural Models of Codecited by 2
  5. 2023Redundancy and Concept Analysis for Code-trained Language Modelscited by 1
  6. 2024Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectorscited by 0
  7. 2025From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agentscited by 0