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.
GiFT: Gibbs Fine-Tuning for Code Generation
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness
Diversified Sampling Improves Scaling LLM inference
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping
SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
An Interpretable Automated Mechanism Design Framework with Large Language Models
Performance Review on LLM for solving leetcode problems
1bit-Merging: Dynamic Quantized Merging for Large Language Models
CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation
3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning
CRANE: Reasoning with constrained LLM generation
RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
Enhancing LLM Character-Level Manipulation via Divide and Conquer
From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework
Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
Verifying LLM-Generated Code in the Context of Software Verification with Ada/SPARK
Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights
Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering
LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks
SnipGen: A Mining Repository Framework for Evaluating LLMs for Code
Cardiverse: Harnessing LLMs for Novel Card Game Prototyping
What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces
Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning
Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Proving the Coding Interview: A Benchmark for Formally Verified Code Generation
Optimistic Gradient Learning with Hessian Corrections for High-Dimensional Black-Box Optimization
nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow
Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning
CodeSCM: Causal Analysis for Multi-Modal Code Generation
Teaching Language Models to Critique via Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.