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.
Insights from the Usage of the Ansible Lightspeed Code Completion Service
DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation
HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
How Do Humans Write Code? Large Models Do It the Same Way Too
Unlocking the Power of Large Language Models for Entity Alignment
Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Test-Driven Development for Code Generation
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
Advancing GenAI Assisted Programming--A Comparative Study on Prompt Efficiency and Code Quality Between GPT-4 and GLM-4
RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian
HumanEval on Latest GPT Models -- 2024
EVOR: Evolving Retrieval for Code Generation
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation
Exploring Hybrid Question Answering via Program-based Prompting
CodeMind: Evaluating Large Language Models for Code Reasoning
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
MPIrigen: MPI Code Generation through Domain-Specific Language Models
DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
Instruction Tuning for Secure Code Generation
Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models
Game Agent Driven by Free-Form Text Command: Using LLM-based Code Generation and Behavior Branch
GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Grounding Data Science Code Generation with Input-Output Specifications
LLMs for Coding and Robotics Education
V-STaR: Training Verifiers for Self-Taught Reasoners
Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.