Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
- URL: http://arxiv.org/abs/2407.21077v1
- Date: Mon, 29 Jul 2024 20:42:59 GMT
- Title: Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
- Authors: Somshubra Majumdar, Vahid Noroozi, Sean Narenthiran, Aleksander Ficek, Jagadeesh Balam, Boris Ginsburg,
- Abstract summary: We introduce a scalable method for generating synthetic instructions to enhance the code generation capability of Large Language Models.
The proposed algorithm, Genetic-Instruct, mimics evolutionary processes, utilizing self-instruction to create numerous synthetic samples from a limited number of seeds.
- Score: 54.51932175059004
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) rely on instruction samples for alignment, but creating these datasets poses challenges, particularly in expert-dependent tasks like coding, which can be cost-prohibitive. One approach to mitigate these challenges is synthesizing data using another LLM. In this paper, we introduce a scalable method for generating synthetic instructions to enhance the code generation capability of LLMs. The proposed algorithm, Genetic-Instruct, mimics evolutionary processes, utilizing self-instruction to create numerous synthetic samples from a limited number of seeds. Genetic-Instruct is designed for efficient scaling of the generation process. Fine-tuning multiple coding LLMs with the synthetic samples demonstrates a significant improvement in their code generation accuracy compared to the baselines.
Related papers
- SnipGen: A Mining Repository Framework for Evaluating LLMs for Code [51.07471575337676]
Language Models (LLMs) are trained on extensive datasets that include code repositories.
evaluating their effectiveness poses significant challenges due to the potential overlap between the datasets used for training and those employed for evaluation.
We introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering across various downstream tasks for code generation.
arXiv Detail & Related papers (2025-02-10T21:28:15Z) - EpiCoder: Encompassing Diversity and Complexity in Code Generation [49.170195362149386]
We introduce a novel feature tree-based synthesis framework inspired by Abstract Syntax Trees (AST)
Unlike AST, which captures syntactic structure of code, our framework models semantic relationships between code elements.
We fine-tuned widely-used base models to create the EpiCoder series, achieving state-of-the-art performance at both the function and file levels.
arXiv Detail & Related papers (2025-01-08T18:58:15Z) - EPiC: Cost-effective Search-based Prompt Engineering of LLMs for Code Generation [8.009881267479189]
Large Language Models (LLMs) have seen increasing use in various software development tasks, especially in code generation.
We propose an alternative approach named Evolutionary Prompt Engineering for Code (EPiC) to evolve the original prompts toward better ones that produce high-quality code.
Our evaluation against state-of-the-art (SOTA) LLM-based code generation models shows that EPiC outperforms all the baselines in terms of cost-effectiveness.
arXiv Detail & Related papers (2024-08-20T21:15:36Z) - Case2Code: Scalable Synthetic Data for Code Generation [105.89741089673575]
Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.
Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs.
We propose a textbfCase2Code task by exploiting the expressiveness and correctness of programs.
arXiv Detail & Related papers (2024-07-17T11:35:00Z) - CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities.
We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution.
We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
arXiv Detail & Related papers (2024-04-08T21:15:36Z) - StepCoder: Improve Code Generation with Reinforcement Learning from
Compiler Feedback [58.20547418182074]
We introduce StepCoder, a novel framework for code generation, consisting of two main components.
CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks.
FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization.
Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
arXiv Detail & Related papers (2024-02-02T13:14:31Z) - Exploring Large Language Models for Code Explanation [3.2570216147409514]
Large Language Models (LLMs) have made remarkable strides in Natural Language Processing.
This study specifically delves into the task of generating natural-language summaries for code snippets, using various LLMs.
arXiv Detail & Related papers (2023-10-25T14:38:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.