mlsanityData to 7 Oct 2026

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

arXiv 2310.17903 ↗First posted 27 Oct 2023cs.SE cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case generation. Despite their great potential, language models for code intelligence (LM4Code) are susceptible to potential pitfalls, which hinder realistic performance and further impact their reliability and applicability in real-world deployment. Such challenges drive the need for a comprehensive understanding - not just identifying these issues but delving into their possible implications and existing solutions to build more reliable language models tailored to code intelligence. Based on a well-defined systematic research approach, we conducted an extensive literature review to uncover the pitfalls inherent in LM4Code. Finally, 67 primary studies from top-tier venues have been identified. After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems. We developed a comprehensive classification scheme that dissects pitfalls across four crucial aspects: data collection and labeling, system design and learning, performance evaluation, and deployment and maintenance. Through this study, we aim to provide a roadmap for researchers and practitioners, facilitating their understanding and utilization of LM4Code in reliable and trustworthy ways.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 101 of its 192 references that are in the map. First posted on arXiv 27 Oct 2023.

Builds on

101 of 192 references.

References · 101

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2020Extracting Training Data from Large Language Modelscited by 2,144
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  6. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  7. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  10. 2023A Watermark for Large Language Modelscited by 667
  11. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  12. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
38 more
  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  2. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  3. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 417
  4. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  5. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 411
  6. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  7. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  8. 2022A Systematic Evaluation of Large Language Models of Codecited by 360
  9. 2018Model compression via distillation and quantizationcited by 287
  10. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
  11. 2020IntelliCode Compose: Code Generation Using Transformercited by 225
  12. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  13. 2021Trustworthy AI: From Principles to Practicescited by 206
  14. 2018Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflowcited by 165
  15. 2023Software Testing with Large Language Models: Survey, Landscape, and Visioncited by 163
  16. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  17. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  18. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  19. 2020Deep Learning based Vulnerability Detection: Are We There Yet?cited by 142
  20. 2020You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completioncited by 112
  21. 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
  22. 2021Examining Zero-Shot Vulnerability Repair with Large Language Modelscited by 105
  23. 2021Jigsaw: Large Language Models meet Program Synthesiscited by 103
  24. 2022ReCode: Robustness Evaluation of Code Generation Modelscited by 100
  25. 2018Improving Automatic Source Code Summarization via Deep Reinforcement Learningcited by 99
  26. 2020Compressing Large-Scale Transformer-Based Models: A Case Study on BERTcited by 95
  27. 2022Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programmingcited by 91
  28. 2023Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issuescited by 78
  29. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  30. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  31. 2016Latent Predictor Networks for Code Generationcited by 73
  32. 2022Natural Attack for Pre-trained Models of Codecited by 72
  33. 2020Compression of Deep Learning Models for Text: A Surveycited by 64
  34. 2023On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilotcited by 64
  35. 2021Vulnerability Detection with Fine-grained Interpretationscited by 56
  36. 2022What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Codecited by 50
  37. 2023How Effective Are Neural Networks for Fixing Security Vulnerabilitiescited by 50
  38. 2021D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysiscited by 48

50 most cited of 101 All 101 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 4.

9 papers.

  1. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  2. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  3. 2024Human-In-the-Loop Software Development Agentscited by 42
  4. 2025On Benchmarking Code LLMs for Android Malware Analysiscited by 12
  5. 2026RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassiancited by 6
  6. 2026HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automationcited by 5
  7. 2024Code LLMs: A Taxonomy-based Surveycited by 3
  8. 2026SWE-QA: A Dataset and Benchmark for Complex Code Understandingcited by 2
  9. 2026A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directionscited by 0