# Towards Understanding What Code Language Models Learned

arXiv: https://arxiv.org/abs/2306.11943 · HTML: https://mlsanity.com/paper/2306.11943/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 20 Jun 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [The Adverse Effects of Code Duplication in Machine Learning Models of Code](https://mlsanity.com/paper/1812.06469/) (2018)
- [CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://mlsanity.com/paper/2305.02309/) (2023)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Contrastive Code Representation Learning](https://mlsanity.com/paper/2007.04973/) (2020)
- [NatGen: Generative pre-training by "Naturalizing" source code](https://mlsanity.com/paper/2206.07585/) (2022)
- [What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code](https://mlsanity.com/paper/2202.06840/) (2022)
- [Semantic Robustness of Models of Source Code](https://mlsanity.com/paper/2002.03043/) (2020)
- [What do pre-trained code models know about code?](https://mlsanity.com/paper/2108.11308/) (2021)
- [Emergent Representations of Program Semantics in Language Models Trained on Programs](https://mlsanity.com/paper/2305.11169/) (2023)
- [Probing Pretrained Models of Source Code](https://mlsanity.com/paper/2202.08975/) (2022)
- [NOPE: A Corpus of Naturally-Occurring Presuppositions in English](https://mlsanity.com/paper/2109.06987/) (2021)
- [Redundancy and Concept Analysis for Code-trained Language Models](https://mlsanity.com/paper/2305.00875/) (2023)

## Built on by (most cited first, 3 of 3)

- [Do Current Language Models Support Code Intelligence for R Programming Language?](https://mlsanity.com/paper/2410.07793/) (2024)
- [ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding](https://mlsanity.com/paper/2504.00019/) (2025)
- [Towards Understanding What State Space Models Learn About Code](https://mlsanity.com/paper/2602.06774/) (2026)

## Abstract (arXiv)

Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding language. To understand the extent to which language models can learn some form of meaning, we investigate their ability to capture semantics of code beyond superficial frequency and co-occurrence. In contrast to previous research on probing models for linguistic features, we study pre-trained models in a setting that allows for objective and straightforward evaluation of a model's ability to learn semantics. In this paper, we examine whether such models capture the semantics of code, which is precisely and formally defined. Through experiments involving the manipulation of code fragments, we show that code pre-trained models of code learn a robust representation of the computational semantics of code that goes beyond superficial features of form alone