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.
Assessing GPT4-V on Structured Reasoning Tasks
Rethinking the Instruction Quality: LIFT is What You Need
ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity
Batched Low-Rank Adaptation of Foundation Models
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs
DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions
Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data
A Machine Learning Approach Towards SKILL Code Autocompletion
Magicoder: Empowering Code Generation with OSS-Instruct
Recursive Visual Programming
Zero-Shot Video Question Answering with Procedural Programs
Universal Self-Consistency for Large Language Model Generation
Self-Infilling Code Generation
LLMs for Science: Usage for Code Generation and Data Analysis
Function-constrained Program Synthesis
YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model
Untargeted Code Authorship Evasion with Seq2Seq Transformation
LLM-Assisted Code Cleaning For Training Accurate Code Generators
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers
Evaluating In-Context Learning of Libraries for Code Generation
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair
DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack
MELA: Multilingual Evaluation of Linguistic Acceptability
Language Models are Better Bug Detector Through Code-Pair Classification
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
Can LLMs Patch Security Issues?
Anticipating User Needs: Insights from Design Fiction on Conversational Agents for Computational Thinking
CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.