# PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback

arXiv: https://arxiv.org/abs/2307.14936 · HTML: https://mlsanity.com/paper/2307.14936/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 42 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [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)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [SantaCoder: don't reach for the stars!](https://mlsanity.com/paper/2301.03988/) (2023)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)

## Built on by (most cited first, 30 of 69)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [Teaching Large Language Models to Reason with Reinforcement Learning](https://mlsanity.com/paper/2403.04642/) (2024)
- [Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing](https://mlsanity.com/paper/2506.09965/) (2025)
- [Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation](https://mlsanity.com/paper/2308.10335/) (2023)
- [Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code](https://mlsanity.com/paper/2311.07989/) (2023)
- [Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement](https://mlsanity.com/paper/2411.00622/) (2024)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://mlsanity.com/paper/2312.15224/) (2023)
- [CodeJudge: Evaluating Code Generation with Large Language Models](https://mlsanity.com/paper/2410.02184/) (2024)
- [WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning](https://mlsanity.com/paper/2312.14187/) (2023)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [Benchmarking Agentic Workflow Generation](https://mlsanity.com/paper/2410.07869/) (2024)
- [LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks](https://mlsanity.com/paper/2502.06215/) (2025)
- [MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning](https://mlsanity.com/paper/2311.02303/) (2023)
- [Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering](https://mlsanity.com/paper/2311.06503/) (2023)
- [ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback](https://mlsanity.com/paper/2409.14826/) (2024)
- [CodeS: Natural Language to Code Repository via Multi-Layer Sketch](https://mlsanity.com/paper/2403.16443/) (2024)
- [LLM-Empowered State Representation for Reinforcement Learning](https://mlsanity.com/paper/2407.13237/) (2024)
- [Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.18676/) (2024)
- [LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression](https://mlsanity.com/paper/2309.14021/) (2023)
- [BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models](https://mlsanity.com/paper/2308.16458/) (2023)
- [Competition-Level Problems are Effective LLM Evaluators](https://mlsanity.com/paper/2312.02143/) (2023)
- [Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning](https://mlsanity.com/paper/2409.12452/) (2024)
- [Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance](https://mlsanity.com/paper/2411.03562/) (2024)
- [Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2401.00788/) (2024)
- [LLM for SoC Security: A Paradigm Shift](https://mlsanity.com/paper/2310.06046/) (2023)
- [Tool-Augmented Reward Modeling](https://mlsanity.com/paper/2310.01045/) (2023)

## Abstract (arXiv)

Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.