Papers with Code 아카이브

Code Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/yongkdu/faircoder

공식 코드

FairCoder: Evaluating Social Bias of LLMs in Code Generation

https://github.com/you68681/lpw

공식 코드

Planning-Driven Programming: A Large Language Model Programming Workflow

https://github.com/ypapanik/t5-for-code-generation

공식 코드

Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers

https://github.com/yuchen814/codehalu

공식 코드

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification

https://github.com/yueyuel/reliablelm4code

공식 코드

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

https://github.com/yule-BUAA/MergeLLM

공식 코드

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

https://github.com/yuxixie/coral

공식 코드

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement

https://github.com/yxwan123/logicasker

공식 코드

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models

https://github.com/yz1019117968/fse-24-unitrans

공식 코드

Exploring and Unleashing the Power of Large Language Models in Automated Code Translation

https://github.com/zh19980811/Style2Code

공식 코드

Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning

https://github.com/zhangzhengde0225/Xiwu

공식 코드

Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics

https://github.com/zhihan72/chart2code

공식 코드

Enhancing Chart-to-Code Generation in Multimodal Large Language Models via Iterative Dual Preference Learning

https://github.com/zhuohaoyu/orps

공식 코드

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

https://github.com/zichenwen1/dija

공식 코드

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

https://github.com/ziyangjoy/comera

공식 코드

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization

https://github.com/ziyangjoy/diablo

공식 코드

DiaBlo: Diagonal Blocks Are Sufficient For Finetuning

https://github.com/zju-ctag/b4

공식 코드

B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests

https://github.com/zju-d3/uilm

공식 코드

UI Layers Merger: Merging UI layers via Visual Learning and Boundary Prior

https://github.com/zjunlp/easyinstruct

공식 코드

When Do Program-of-Thoughts Work for Reasoning?

https://github.com/zjunlp/recode

공식 코드

ReCode: Updating Code API Knowledge with Reinforcement Learning

https://github.com/zkx06111/algo

공식 코드

ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers

https://github.com/zorazrw/multilingual-conala

공식 코드

MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages

https://github.com/zorazrw/odex

공식 코드

Execution-Based Evaluation for Open-Domain Code Generation

https://github.com/ztwater/instruct-or-interact

공식 코드

Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering

https://github.com/zyq-scut/rltf

공식 코드

RLTF: Reinforcement Learning from Unit Test Feedback

https://github.com/zysszy/GrammarCNN

공식 코드

A Grammar-Based Structural CNN Decoder for Code Generation

https://github.com/zysszy/TreeGen

공식 코드

TreeGen: A Tree-Based Transformer Architecture for Code Generation

https://github.com/zyzisastudyreallyhardguy/llm4sd

공식 코드

Large Language Models for Scientific Synthesis, Inference and Explanation

https://gitlab.com/codegenfact/BertranX

공식 코드

The impact of lexical and grammatical processing on generating code from natural language

https://gitlab.com/codegenfactors/BertranX

공식 코드

The impact of lexical and grammatical processing on generating code from natural language

https://worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd

공식 코드

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

https://zenodo.org/record/7875623

공식 코드

Using Large Language Models to Generate JUnit Tests: An Empirical Study

https://codigos.ufsc.br/lapix/Sketch2AIA

Automatic code generation from sketches of mobile applications in end-user development using Deep Learning

https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama

LLaMA: Open and Efficient Foundation Language Models

https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/codegen

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/gpt_bigcode

SantaCoder: don't reach for the stars!

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.