Papers with Code 아카이브

Code Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/SqueezeAILab/SqueezedAttention

공식 코드

Squeezed Attention: Accelerating Long Context Length LLM Inference

https://github.com/THUDM/CodeGeeX

공식 코드

CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X

https://github.com/Tianyi2/IaCGen

공식 코드

Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework

https://github.com/UKPLab/arxiv2024-IRCoder

공식 코드

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

https://github.com/UKPLab/iclr2025-obscura-coder

공식 코드

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

https://github.com/VichyTong/CodeJudge

공식 코드

CodeJudge: Evaluating Code Generation with Large Language Models

https://github.com/VulScribeR/VulScribeR

공식 코드

VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs

https://github.com/WangXinglin/FSC

공식 코드

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation

https://github.com/XMZhangAI/Seeker

공식 코드

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework

https://github.com/XpastaX/Instruction-Fusion

공식 코드

Instruction Fusion: Advancing Prompt Evolution through Hybridization

https://github.com/YerbaPage/MGDebugger

공식 코드

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

https://github.com/YihongDong/CODEP

공식 코드

CodePAD: Sequence-based Code Generation with Pushdown Automaton

https://github.com/YuanJiangGit/EnhancedCQ

공식 코드

Enhancing High-Quality Code Generation in Large Language Models with Comparative Prefix-Tuning

https://github.com/Zeqiang-Lai/MiniDALLE-3

공식 코드

Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models

https://github.com/Zhehui-Huang/LLM_Routing

공식 코드

Can Large Language Models Solve Robot Routing?

https://github.com/ablustrund/apps_plus

공식 코드

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

https://github.com/acadlab/spicepilot

공식 코드

SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance

https://github.com/adamkhakhar/python-pac-code-prediction-set

공식 코드

PAC Prediction Sets for Large Language Models of Code

https://github.com/adf1178/pt4code

공식 코드

No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence

https://github.com/agemagician/CodeTrans

공식 코드

CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing

https://github.com/agi-edgerunners/llm-adapters

공식 코드

Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models

https://github.com/agi-eval-official/corecodebench

공식 코드

CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark

https://github.com/alex-haochenli/gift

공식 코드

GiFT: Gibbs Fine-Tuning for Code Generation

https://github.com/alex-haochenli/reco

공식 코드

Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search

https://github.com/alexjjjchen/compliance-to-code

공식 코드

Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation

https://github.com/alibaba/cloudeval-yaml

공식 코드

CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation

https://github.com/aliwister/ast-icl

공식 코드

Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text

https://github.com/allanraventos/refine

공식 코드

Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning

https://github.com/allenai/discoverybench

공식 코드

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

https://github.com/allenai/genesys

공식 코드

Language Modeling by Language Models

https://github.com/alphadl/oop-eval

공식 코드

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models

https://github.com/amazon-research/mbxp-exec-eval

공식 코드

Multi-lingual Evaluation of Code Generation Models

https://github.com/amazon-science/llm-code-preference

공식 코드

Learning Code Preference via Synthetic Evolution

https://github.com/amazon-science/recode

공식 코드

ReCode: Robustness Evaluation of Code Generation Models

https://github.com/amom-nar/amom

공식 코드

AMOM: Adaptive Masking over Masking for Conditional Masked Language Model

https://github.com/andyz245/LanguageAgentTreeSearch

공식 코드

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.