Detecting Functional Memorization in Code Language Models
Matthieu Meeus, Anil Ramakrishna, Shengyuan Hu, Matthew Grange, Zheng Xu, Luca Melis
cs.LG, cs.CL, cs.CR
Submitted: 2026-08-20
Updated: 2026-08-24
Terminology
Sources
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Extracting alignment data in open models
- The Llama 3 Herd of Models
- HyClone: Bridging LLM Understanding and Dynamic Execution for Semantic Code Clone Detection
- How much do language models memorize?
- How Small Transformation Expose the Weakness of Semantic Similarity Measures
- Olmo 3
- CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
- Code Llama: Open Foundation Models for Code
- Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks