# SelfCodeAlign: Self-Alignment for Code Generation

arXiv: https://arxiv.org/abs/2410.24198 · HTML: https://mlsanity.com/paper/2410.24198/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 64 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Builds on (most cited first, 30 of 45)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [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)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [Self-Alignment with Instruction Backtranslation](https://mlsanity.com/paper/2308.06259/) (2023)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Learning Performance-Improving Code Edits](https://mlsanity.com/paper/2302.07867/) (2023)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)

## Built on by (most cited first, 30 of 62)

- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding](https://mlsanity.com/paper/2503.02951/) (2025)
- [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://mlsanity.com/paper/2501.01257/) (2025)
- [OpenCodeReasoning: Advancing Data Distillation for Competitive Coding](https://mlsanity.com/paper/2504.01943/) (2025)
- [OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs](https://mlsanity.com/paper/2504.04030/) (2025)
- [LongCat-Flash Technical Report](https://mlsanity.com/paper/2509.01322/) (2025)
- [ProSec: Fortifying Code LLMs with Proactive Security Alignment](https://mlsanity.com/paper/2411.12882/) (2024)
- [HardTests: Synthesizing High-Quality Test Cases for LLM Coding](https://mlsanity.com/paper/2505.24098/) (2025)
- [DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI](https://mlsanity.com/paper/2512.16676/) (2025)
- [A Technical Survey of Reinforcement Learning Techniques for Large Language Models](https://mlsanity.com/paper/2507.04136/) (2025)
- [A Survey on LLM Mid-Training](https://mlsanity.com/paper/2510.23081/) (2025)
- [EpiCoder: Encompassing Diversity and Complexity in Code Generation](https://mlsanity.com/paper/2501.04694/) (2025)
- [PurpCode: Reasoning for Safer Code Generation](https://mlsanity.com/paper/2507.19060/) (2025)
- [GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation](https://mlsanity.com/paper/2504.10046/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Propose, Solve, Verify: Self-Play Through Formal Verification](https://mlsanity.com/paper/2512.18160/) (2025)
- [Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences](https://mlsanity.com/paper/2506.00419/) (2025)
- [DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs](https://mlsanity.com/paper/2411.13611/) (2024)
- [Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning](https://mlsanity.com/paper/2502.13820/) (2025)
- [RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation](https://mlsanity.com/paper/2502.09183/) (2025)
- [Towards Formal Verification of LLM-Generated Code from Natural Language Prompts](https://mlsanity.com/paper/2507.13290/) (2025)
- [DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation](https://mlsanity.com/paper/2503.10452/) (2025)
- [R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation](https://mlsanity.com/paper/2504.04699/) (2025)
- [Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model](https://mlsanity.com/paper/2602.07422/) (2026)
- [Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?](https://mlsanity.com/paper/2503.05507/) (2025)
- [The Code Barrier: What LLMs Actually Understand?](https://mlsanity.com/paper/2504.10557/) (2025)
- [Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines](https://mlsanity.com/paper/2505.15874/) (2025)
- [CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback](https://mlsanity.com/paper/2507.22080/) (2025)
- [Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment](https://mlsanity.com/paper/2508.04865/) (2025)

## Abstract (arXiv)

Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates them in a sandbox environment. Finally, passing examples are selected for instruction tuning. In our primary experiments, we use SelfCodeAlign with CodeQwen1.5-7B to generate a dataset of 74k instruction-response pairs. Finetuning on this dataset leads to a model that achieves a 67.1 pass@1 on HumanEval+, surpassing CodeLlama-70B-Instruct despite being ten times smaller. Across all benchmarks, this finetuned model consistently outperforms the original version trained with OctoPack, the previous state-of-the-art method for instruction tuning without human annotations or distillation. Additionally, we show that SelfCodeAlign is effective across LLMs of various sizes, from 3B to 33B, and that the base models can benefit more from alignment with their own data distribution. We further validate each component's effectiveness in our pipeline, showing that SelfCodeAlign outperforms both direct distillation from GPT-4o and leading GPT-3.5-based distillation methods, such as OSS-Instruct and Evol-Instruct. SelfCodeAlign has also led to the creation of StarCoder2-Instruct, the first fully transparent, permissively licensed, and self-aligned code LLM that achieves state-of-the-art coding performance.