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/open-compass/devbench

공식 코드

Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study

https://github.com/open-compass/deveval

공식 코드

Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study

https://github.com/open-compass/saga

공식 코드

Rethinking Verification for LLM Code Generation: From Generation to Testing

https://github.com/openai/evals

공식 코드

GPT-4 Technical Report

https://github.com/openai/human-eval

공식 코드

Evaluating Large Language Models Trained on Code

https://github.com/openbmb/eurus

공식 코드

Advancing LLM Reasoning Generalists with Preference Trees

https://github.com/openbmb/repoagent

공식 코드

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

https://github.com/openpsi-project/realhf

공식 코드

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

https://github.com/optml-group/claw-sat

공식 코드

CLAWSAT: Towards Both Robust and Accurate Code Models

https://github.com/osslab-pku/licoeval

공식 코드

LiCoEval: Evaluating LLMs on License Compliance in Code Generation

https://github.com/osslab-pku/llm_compliance

공식 코드

LiCoEval: Evaluating LLMs on License Compliance in Code Generation

https://github.com/oyy2000/layeradvpatcher

공식 코드

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

https://github.com/ozyyshr/repograph

공식 코드

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

https://github.com/p-lambda/composed_finetuning

공식 코드

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

https://github.com/p-lambda/unlabeled_outputs

공식 코드

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

https://github.com/para-lost/rvp

공식 코드

Recursive Visual Programming

https://github.com/parallelcodefoundry/ParEval

공식 코드

Can Large Language Models Write Parallel Code?

https://github.com/parrotsky/autodice

공식 코드

AutoDiCE: Fully Automated Distributed CNN Inference at the Edge

https://github.com/pcyin/tranX

공식 코드

TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

https://github.com/pingbowen23/longdpo

공식 코드

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information

https://github.com/pku-liang/origen

공식 코드

OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection

https://github.com/plasma-umass/pythoness

공식 코드

Effective LLM-Driven Code Generation with Pythoness

https://github.com/pmineiro/musique-off

공식 코드

Online Joint Fine-tuning of Multi-Agent Flows

https://github.com/poldrack/ai-coding-experiments

공식 코드

AI-assisted coding: Experiments with GPT-4

https://github.com/pootiet/explain-then-translate

공식 코드

Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations

https://github.com/portal-cornell/mucode

공식 코드

Multi-Turn Code Generation Through Single-Step Rewards

https://github.com/pppa2019/contexualdynamicmapping

공식 코드

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping

https://github.com/pppa2019/mango

공식 코드

Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective

https://github.com/princeton-nlp/intercode

공식 코드

InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

https://github.com/prithwishjana/cotran

공식 코드

CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution

https://github.com/prnshv/oran-bench-13k

공식 코드

ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks

https://github.com/projectnuwa/layoutnuwa

공식 코드

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

https://github.com/purduedigitaltwin/lampilot

공식 코드

LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs

https://github.com/pytorch/fbgemm

공식 코드

FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference

https://github.com/qing-yuan233/RMCBench

공식 코드

RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code

https://github.com/qiushisun/transcoder

공식 코드

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills

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