# CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

arXiv: https://arxiv.org/abs/2408.13366 · HTML: https://mlsanity.com/paper/2408.13366/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 16 of 16)

- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering](https://mlsanity.com/paper/2404.17723/) (2024)
- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [Latent Predictor Networks for Code Generation](https://mlsanity.com/paper/1603.06744/) (2016)
- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials](https://mlsanity.com/paper/2306.06482/) (2023)
- [Answer is All You Need: Instruction-following Text Embedding via Answering the Question](https://mlsanity.com/paper/2402.09642/) (2024)
- [Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance](https://mlsanity.com/paper/2404.08817/) (2024)
- [The strain on scientific publishing](https://mlsanity.com/paper/2309.15884/) (2023)
- [Enhancing Text-to-SQL Translation for Financial System Design](https://mlsanity.com/paper/2312.14725/) (2023)

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

- [AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers](https://mlsanity.com/paper/2504.20115/) (2025)
- [From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence](https://mlsanity.com/paper/2605.28371/) (2026)
- [Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents](https://mlsanity.com/paper/2512.02812/) (2025)

## Abstract (arXiv)

This paper presents CodeRefine, a novel framework for automatically transforming research paper methodologies into functional code using Large Language Models (LLMs). Our multi-step approach first extracts and summarizes key text chunks from papers, analyzes their code relevance, and creates a knowledge graph using a predefined ontology. Code is then generated from this structured representation and enhanced through a proposed retrospective retrieval-augmented generation approach. CodeRefine addresses the challenge of bridging theoretical research and practical implementation, offering a more accurate alternative to LLM zero-shot prompting. Evaluations on diverse scientific papers demonstrate CodeRefine's ability to improve code implementation from the paper, potentially accelerating the adoption of cutting-edge algorithms in real-world applications.