# When Names Disappear: Revealing What LLMs Actually Understand About Code

arXiv: https://arxiv.org/abs/2510.03178 · HTML: https://mlsanity.com/paper/2510.03178/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 3 Oct 2025.

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

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [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)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [ReCode: Robustness Evaluation of Code Generation Models](https://mlsanity.com/paper/2212.10264/) (2022)
- [The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models](https://mlsanity.com/paper/2406.05761/) (2024)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [Natural Attack for Pre-trained Models of Code](https://mlsanity.com/paper/2201.08698/) (2022)
- [CodeScore: Evaluating Code Generation by Learning Code Execution](https://mlsanity.com/paper/2301.09043/) (2023)
- [xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval](https://mlsanity.com/paper/2303.03004/) (2023)
- [Reasoning Runtime Behavior of a Program with LLM: How Far Are We?](https://mlsanity.com/paper/2403.16437/) (2024)
- [BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies](https://mlsanity.com/paper/2401.15481/) (2024)
- [Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data](https://mlsanity.com/paper/2305.19912/) (2023)
- [SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs](https://mlsanity.com/paper/2504.14757/) (2025)
- [CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs](https://mlsanity.com/paper/2410.01999/) (2024)
- [CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2309.01940/) (2023)
- [Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates](https://mlsanity.com/paper/2402.05980/) (2024)
- [Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension](https://mlsanity.com/paper/2207.11104/) (2022)
- [Structure-aware Fine-tuning for Code Pre-trained Models](https://mlsanity.com/paper/2404.07471/) (2024)

## Built on by (most cited first, 4 of 4)

- [Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning](https://mlsanity.com/paper/2601.23169/) (2026)
- [Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study](https://mlsanity.com/paper/2605.20049/) (2026)
- [TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation](https://mlsanity.com/paper/2607.23425/) (2026)
- [ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments](https://mlsanity.com/paper/2607.24964/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) achieve strong results on code tasks, but how they derive program meaning remains unclear. We argue that code communicates through two channels: structural semantics, which define formal behavior, and human-interpretable naming, which conveys intent. Removing the naming channel severely degrades intent-level tasks such as summarization, where models regress to line-by-line descriptions. Surprisingly, we also observe consistent reductions on execution tasks that should depend only on structure, revealing that current benchmarks reward memorization of naming patterns rather than genuine semantic reasoning. To disentangle these effects, we introduce a suite of semantics-preserving obfuscations and show that they expose identifier leakage across both summarization and execution. Building on these insights, we release ClassEval-Obf, an obfuscation-enhanced benchmark that systematically suppresses naming cues while preserving behavior. Our results demonstrate that ClassEval-Obf reduces inflated performance gaps, weakens memorization shortcuts, and provides a more reliable basis for assessing LLMs' code understanding and generalization.