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.
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation
On Explaining (Large) Language Models For Code Using Global Code-Based Explanations
RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation
LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models
LLM-Aided Customizable Profiling of Code Data Based On Programming Language Concepts
Automatic MILP Model Construction for Multi-Robot Task Allocation and Scheduling Based on Large Language Models
The KoLMogorov Test: Compression by Code Generation
Synthetic Data Generation Using Large Language Models: Advances in Text and Code
Speculative Decoding for Verilog: Speed and Quality, All in One
Can LLMs Enable Verification in Mainstream Programming?
XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
A Comprehensive Study of LLM Secure Code Generation
A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation
VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination
LLM Test Generation via Iterative Hybrid Program Analysis
CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings
Unveiling Pitfalls: Understanding Why AI-driven Code Agents Fail at GitHub Issue Resolution
Can LLMs Formally Reason as Abstract Interpreters for Program Analysis?
TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation
Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models
VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric
LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks
Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms
Collaboration is all you need: LLM Assisted Safe Code Translation
ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction Tuning
Compute Optimal Scaling of Skills: Knowledge vs Reasoning
Capturing Semantic Flow of ML-based Systems
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation
Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression
From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
LocAgent: Graph-Guided LLM Agents for Code Localization
Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.