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/mrflogs/LoRA-Pro

공식 코드

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

https://github.com/mtoles/BeNYfits-ProADA

공식 코드

Program Synthesis Dialog Agents for Interactive Decision-Making

https://github.com/mulns/text2qr

공식 코드

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

https://github.com/multimodal-art-projection/I-SHEEP

공식 코드

I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm

https://github.com/murraytom/cov-eval

공식 코드

Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective

https://github.com/mvasiliniuc/iva-codeint-mobile

공식 코드

Case Study: Using AI-Assisted Code Generation In Mobile Teams

https://github.com/nathanaelbeau/codeinsight

공식 코드

CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow

https://github.com/naver/gdc

공식 코드

Controlling Conditional Language Models without Catastrophic Forgetting

https://github.com/nb15/codeSCM-naacl25

공식 코드

CodeSCM: Causal Analysis for Multi-Modal Code Generation

https://github.com/neucol/llm-conversion-performance

공식 코드

Leveraging Large Language Models for Code Translation and Software Development in Scientific Computing

https://github.com/neuir/coast

공식 코드

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

https://github.com/neuir/intervenor

공식 코드

INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair

https://github.com/neulab/code-bert-score

공식 코드

CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code

https://github.com/neulab/external-knowledge-codegen

공식 코드

Incorporating External Knowledge through Pre-training for Natural Language to Code Generation

https://github.com/niansong1996/lever

공식 코드

LEVER: Learning to Verify Language-to-Code Generation with Execution

https://github.com/nicoladainese96/code-world-models

공식 코드

Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search

https://github.com/nicolae-teodor-pavel/commit-message-generation

공식 코드

A Sketch-Based Neural Model for Generating Commit Messages from Diffs

https://github.com/ninjatech-ai/mple

공식 코드

Multi-Programming Language Ensemble for Code Generation in Large Language Model

https://github.com/niujuxin/rechisel

공식 코드

ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection

https://github.com/nizarislah/gitchameleon

공식 코드

GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models

https://github.com/nju-websoft/paircoder

공식 코드

A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement

https://github.com/nl2code/attentioncoder

공식 코드

Improving Natural Language Capability of Code Large Language Model

https://github.com/nlpxucan/wizardlm

공식 코드

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

https://github.com/novasky-ai/skythought

공식 코드

S*: Test Time Scaling for Code Generation

https://github.com/ntt-dkiku/chaos-eater

공식 코드

ChaosEater: Fully Automating Chaos Engineering with Large Language Models

https://github.com/ntunlp/chatgpt_eval

공식 코드

A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets

https://github.com/nuprl/multipl-e

공식 코드

MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation

https://github.com/nvlabs/craftrtl

공식 코드

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

https://github.com/nvlabs/cvdp_benchmark

공식 코드

Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification

https://github.com/nvlabs/fveval

공식 코드

FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware

https://github.com/nvlabs/verilog-eval

공식 코드

VerilogEval: Evaluating Large Language Models for Verilog Code Generation

https://github.com/nweir127/cogex

공식 코드

Learning to Reason via Program Generation, Emulation, and Search

https://github.com/nyu-mll/ILF-for-code-generation

공식 코드

Improving Code Generation by Training with Natural Language Feedback

https://github.com/observerw/chisellm

공식 코드

ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development

https://github.com/ofa-sys/gsm8k-screl

공식 코드

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

https://github.com/onekq/webapp1k

공식 코드

WebApp1K: A Practical Code-Generation Benchmark for Web App Development

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