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.
LSR-MCTS: Alleviating Long Range Dependency in Code Generation
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
Boosting Universal LLM Reward Design through the Heuristic Reward Observation Space Evolution
PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning
Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search
DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation
How Accurately Do Large Language Models Understand Code?
OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
Do LLM Evaluators Prefer Themselves for a Reason?
NAACL2025 Tutorial: Adaptation of Large Language Models
MG-Gen: Single Image to Motion Graphics Generation with Layer Decomposition
The Self-Learning Agent with a Progressive Neural Network Integrated Transformer
Enhancing Chart-to-Code Generation in Multimodal Large Language Models via Iterative Dual Preference Learning
Pel, A Programming Language for Orchestrating AI Agents
From Code Generation to Software Testing: AI Copilot with Context-Based RAG
On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software
SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking
How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics
MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
TuRTLe: A Unified Evaluation of LLMs for RTL Generation
Carbon Footprint Evaluation of Code Generation through LLM as a Service
CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors
Challenges and Paths Towards AI for Software Engineering
Post-Incorporating Code Structural Knowledge into LLMs via In-Context Learning for Code Translation
RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation
Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models
Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation
Verbal Process Supervision Elicits Better Coding Agents
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.