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.
PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents
Mitigating Gender Bias in Code Large Language Models via Model Editing
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation
What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
Context-Augmented Code Generation Using Programming Knowledge Graphs
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
Generating CAD Code with Vision-Language Models for 3D Designs
In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics
Evaluation of Code LLMs on Geospatial Code Generation
An evaluation of LLM code generation capabilities through graded exercises
Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning
AIME: AI System Optimization via Multiple LLM Evaluators
Tadashi: Enabling AI-Based Automated Code Generation With Guaranteed Correctness
Showing LLM-Generated Code Selectively Based on Confidence of LLMs
Generating Equivalent Representations of Code By A Self-Reflection Approach
Steering Large Language Models between Code Execution and Textual Reasoning
Learning Code Preference via Synthetic Evolution
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation
A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages
CodeJudge: Evaluating Code Generation with Large Language Models
GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance
Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
Not All LLM Reasoners Are Created Equal
AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation
BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data
TRANSAGENT: An LLM-Based Multi-Agent System for Code Translation
LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.