# The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?

arXiv: https://arxiv.org/abs/2402.19475 · HTML: https://mlsanity.com/paper/2402.19475/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 67 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 30 of 45)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification](https://mlsanity.com/paper/2308.07921/) (2023)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [Can Large Language Models Really Improve by Self-critiquing Their Own Plans?](https://mlsanity.com/paper/2310.08118/) (2023)
- [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024)
- [The Generative AI Paradox: "What It Can Create, It May Not Understand"](https://mlsanity.com/paper/2311.00059/) (2023)
- [Execution-Based Evaluation for Open-Domain Code Generation](https://mlsanity.com/paper/2212.10481/) (2022)

## Built on by (most cited first, 20 of 20)

- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [Small Language Models Need Strong Verifiers to Self-Correct Reasoning](https://mlsanity.com/paper/2404.17140/) (2024)
- [Formal Mathematical Reasoning: A New Frontier in AI](https://mlsanity.com/paper/2412.16075/) (2024)
- [CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?](https://mlsanity.com/paper/2408.10718/) (2024)
- [What Makes Large Language Models Reason in (Multi-Turn) Code Generation?](https://mlsanity.com/paper/2410.08105/) (2024)
- [SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs](https://mlsanity.com/paper/2504.14757/) (2025)
- [Learning Code Preference via Synthetic Evolution](https://mlsanity.com/paper/2410.03837/) (2024)
- [MdEval: Massively Multilingual Code Debugging](https://mlsanity.com/paper/2411.02310/) (2024)
- [LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs](https://mlsanity.com/paper/2404.10304/) (2024)
- [ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments](https://mlsanity.com/paper/2505.22169/) (2025)
- [Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?](https://mlsanity.com/paper/2505.10443/) (2025)
- [Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods](https://mlsanity.com/paper/2406.15540/) (2024)
- [IFEvalCode: Controlled Code Generation](https://mlsanity.com/paper/2507.22462/) (2025)
- [XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants](https://mlsanity.com/paper/2503.14281/) (2025)
- [PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation](https://mlsanity.com/paper/2507.14913/) (2025)
- [Self-Execution Simulation Improves Coding Models](https://mlsanity.com/paper/2604.03253/) (2026)
- [Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals](https://mlsanity.com/paper/2505.14597/) (2025)
- [Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code](https://mlsanity.com/paper/2605.05267/) (2026)
- [On the Robustness of LLMs' Internal Representation of Code Correctness](https://mlsanity.com/paper/2608.08266/) (2026)

## Abstract (arXiv)

While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others are more subtle and pass weaker correctness checks such as being able to compile. In this work, we focus on these counterfeit samples: programs sampled from a language model that 1) have a high enough log-probability to be generated at a moderate temperature and 2) pass weak correctness checks. Overall, we discover that most models have a very shallow understanding of counterfeits through three clear failure modes. First, models mistakenly classify them as correct. Second, models are worse at reasoning about the execution behaviour of counterfeits and often predict their execution results as if they were correct. Third, when asking models to fix counterfeits, the likelihood of a model successfully repairing a counterfeit is often even lower than that of sampling a correct program from scratch. Counterfeits also have very unexpected properties: first, counterfeit programs for problems that are easier for a model to solve are not necessarily easier to detect and only slightly easier to execute and repair. Second, counterfeits from a given model are just as confusing to the model itself as they are to other models. Finally, both strong and weak models are able to generate counterfeit samples that equally challenge all models. In light of our findings, we recommend that care and caution be taken when relying on models to understand their own samples, especially when no external feedback is incorporated.