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.
RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents
GitHub Copilot: the perfect Code compLeeter?
CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents
Long Code Arena: a Set of Benchmarks for Long-Context Code Models
DocCGen: Document-based Controlled Code Generation
On the Impacts of Contexts on Repository-Level Code Generation
A Problem-Oriented Perspective and Anchor Verification for Code Optimization
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages
ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models
ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
Is Programming by Example solved by LLMs?
Real2Code: Reconstruct Articulated Objects via Code Generation
CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
Data Augmentation by Fuzzing for Neural Test Generation
We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
Entropy-Reinforced Planning with Large Language Models for Drug Discovery
VersiCode: Towards Version-controllable Code Generation
Transforming Wearable Data into Health Insights using Large Language Model Agents
JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models
SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models
LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning
Scaling Automatic Extraction of Pseudocode
LogiCode: an LLM-Driven Framework for Logical Anomaly Detection
AICoderEval: Improving AI Domain Code Generation of Large Language Models
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation
Online Joint Fine-tuning of Multi-Agent Flows
FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models
Enhancing Repository-Level Code Generation with Integrated Contextual Information
Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks
SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
Re-ReST: Reflection-Reinforced Self-Training for Language Agents
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.