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.
WAFFLE: Finetuning Multi-Modal Model for Automated Front-End Development
An LLM Agent for Automatic Geospatial Data Analysis
Watermarking Large Language Models and the Generated Content: Opportunities and Challenges
Process Supervision-Guided Policy Optimization for Code Generation
MojoBench: Language Modeling and Benchmarks for Mojo
Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition
ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment
GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks
Scattered Forest Search: Smarter Code Space Exploration with LLMs
Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
Automated Proof Generation for Rust Code via Self-Evolution
Self-Explained Keywords Empower Large Language Models for Code Generation
Building A Coding Assistant via the Retrieval-Augmented Language Model
Large Language Models in Computer Science Education: A Systematic Literature Review
mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation
MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification
CELI: Controller-Embedded Language Model Interactions
Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks
LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks
Personality-Guided Code Generation Using Large Language Models
Evolutionary Retrofitting
Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis
Substance Beats Style: Why Beginning Students Fail to Code with LLMs
FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
AFlow: Automating Agentic Workflow Generation
Agent-as-a-Judge: Evaluate Agents with Agents
FLARE: Faithful Logic-Aided Reasoning and Exploration
Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles
Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code
Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
Test-driven Software Experimentation with LASSO: an LLM Prompt Benchmarking Example
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.