Papers with Code 아카이브
Code Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 28
- 보존된 평가 기록
- 241
Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.
Source: Deep Learning for Source Code Modeling and Generation
Image source: Measuring Coding Challenge Competence With APPS
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
AutoDev: Automated AI-Driven Development
Software Vulnerability and Functionality Assessment using LLMs
Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study
Bugs in Large Language Models Generated Code: An Empirical Study
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation
Automatic Generation of Python Programs Using Context-Free Grammars
Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
Materials science in the era of large language models: a perspective
Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
UniSparse: An Intermediate Language for General Sparse Format Customization
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
ProMoAI: Process Modeling with Generative AI
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
Guiding Enumerative Program Synthesis with Large Language Models
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models
Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering
Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
CatCode: A Comprehensive Evaluation Framework for LLMs On the Mixture of Code and Text
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
SynCode: LLM Generation with Grammar Augmentation
LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation
Open Assistant Toolkit -- version 2
Comparing large language models and human programmers for generating programming code
StarCoder 2 and The Stack v2: The Next Generation
Compositional API Recommendation for Library-Oriented Code Generation
The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?
SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation
SoD$^2$: Statically Optimizing Dynamic Deep Neural Network
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Data Interpreter: An LLM Agent For Data Science
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.