# Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings

arXiv: https://arxiv.org/abs/2204.09191 · HTML: https://mlsanity.com/paper/2204.09191/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2022.

## Built on by (most cited first, 10 of 10)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [A systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challenges](https://mlsanity.com/paper/2306.16171/) (2023)
- [IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2505.12442/) (2025)
- [RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry](https://mlsanity.com/paper/2505.15179/) (2025)
- [ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding](https://mlsanity.com/paper/2504.00019/) (2025)
- [An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios](https://mlsanity.com/paper/2402.01723/) (2024)
- [Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models](https://mlsanity.com/paper/2506.09396/) (2025)
- [Instruction Alignment for Binary Code Representation Learning](https://mlsanity.com/paper/2608.11766/) (2026)

## Abstract (arXiv)

Neural program embeddings have demonstrated considerable promise in a range of program analysis tasks, including clone identification, program repair, code completion, and program synthesis. However, most existing methods generate neural program embeddings directly from the program source codes, by learning from features such as tokens, abstract syntax trees, and control flow graphs. This paper takes a fresh look at how to improve program embeddings by leveraging compiler intermediate representation (IR). We first demonstrate simple yet highly effective methods for enhancing embedding quality by training embedding models alongside source code and LLVM IR generated by default optimization levels (e.g., -O2). We then introduce IRGen, a framework based on genetic algorithms (GA), to identify (near-)optimal sequences of optimization flags that can significantly improve embedding quality.