# Toward Neurosymbolic Program Comprehension

arXiv: https://arxiv.org/abs/2502.01806 · HTML: https://mlsanity.com/paper/2502.01806/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 30 of 35)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Will we run out of data? Limits of LLM scaling based on human-generated data](https://mlsanity.com/paper/2211.04325/) (2022)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Neuro-Symbolic Program Synthesis](https://mlsanity.com/paper/1611.01855/) (2016)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design](https://mlsanity.com/paper/2303.07839/) (2023)
- [Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference](https://mlsanity.com/paper/2403.20306/) (2024)
- [Programming with a Differentiable Forth Interpreter](https://mlsanity.com/paper/1605.06640/) (2016)
- [Probing Pretrained Models of Source Code](https://mlsanity.com/paper/2202.08975/) (2022)
- [Learning Continuous Semantic Representations of Symbolic Expressions](https://mlsanity.com/paper/1611.01423/) (2016)
- [Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice](https://mlsanity.com/paper/2404.14901/) (2024)
- [CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution](https://mlsanity.com/paper/2306.06755/) (2023)
- [AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models](https://mlsanity.com/paper/2206.11719/) (2022)
- [WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts](https://mlsanity.com/paper/2402.18956/) (2024)
- [Semantic Code Repair using Neuro-Symbolic Transformation Networks](https://mlsanity.com/paper/1710.11054/) (2017)
- [Toward a Theory of Causation for Interpreting Neural Code Models](https://mlsanity.com/paper/2302.03788/) (2023)
- [Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations](https://mlsanity.com/paper/2407.08983/) (2024)
- [Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar](https://mlsanity.com/paper/2204.06643/) (2022)
- [CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure](https://mlsanity.com/paper/2210.04633/) (2022)
- [Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?](https://mlsanity.com/paper/2401.01512/) (2024)
- [Looking into Black Box Code Language Models](https://mlsanity.com/paper/2407.04868/) (2024)

## Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have paved the way for Large Code Models (LCMs), enabling automation in complex software engineering tasks, such as code generation, software testing, and program comprehension, among others. Tools like GitHub Copilot and ChatGPT have shown substantial benefits in supporting developers across various practices. However, the ambition to scale these models to trillion-parameter sizes, exemplified by GPT-4, poses significant challenges that limit the usage of Artificial Intelligence (AI)-based systems powered by large Deep Learning (DL) models. These include rising computational demands for training and deployment and issues related to trustworthiness, bias, and interpretability. Such factors can make managing these models impractical for many organizations, while their "black-box'' nature undermines key aspects, including transparency and accountability. In this paper, we question the prevailing assumption that increasing model parameters is always the optimal path forward, provided there is sufficient new data to learn additional patterns. In particular, we advocate for a Neurosymbolic research direction that combines the strengths of existing DL techniques (e.g., LLMs) with traditional symbolic methods--renowned for their reliability, speed, and determinism. To this end, we outline the core features and present preliminary results for our envisioned approach, aimed at establishing the first Neurosymbolic Program Comprehension (NsPC) framework to aid in identifying defective code components.