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/qunhualilab/llm-ds-reproducibility

공식 코드

An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science

https://github.com/qurrent-ai/res-q

공식 코드

RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale

https://github.com/qwenlm/qwen2.5-coder

공식 코드

Qwen2.5-Coder Technical Report

https://github.com/qwenlm/qwen3

공식 코드

Qwen3 Technical Report

https://github.com/radzim/obfuscated

공식 코드

LLM Performance for Code Generation on Noisy Tasks

https://github.com/rain9876/auto-code-generator

공식 코드

GAP-Gen: Guided Automatic Python Code Generation

https://github.com/rajarshihaldar/analyze-llm-code-summarization

공식 코드

Analyzing the Performance of Large Language Models on Code Summarization

https://github.com/rajasagashe/juice

공식 코드

JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation

https://github.com/raonikitha/cat-lm

공식 코드

CAT-LM: Training Language Models on Aligned Code And Tests

https://github.com/reddy-lab-code-research/PPOCoder

공식 코드

Execution-based Code Generation using Deep Reinforcement Learning

https://github.com/reddy-lab-code-research/codeattack

공식 코드

CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models

https://github.com/reddy-lab-code-research/structcoder

공식 코드

StructCoder: Structure-Aware Transformer for Code Generation

https://github.com/reds-lab/beear

공식 코드

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

https://github.com/ricardo-larosa/tree-of-thought-llm

공식 코드

Can Github issues be solved with Tree Of Thoughts?

https://github.com/rigorous-software-engineering/nomos

공식 코드

Automatically Testing Functional Properties of Code Translation Models

https://github.com/rioyokotalab/swallow-code-math

공식 코드

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

https://github.com/rise-1210/codeflow

공식 코드

CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation

https://github.com/riselabqueens/forge24-code-translation

공식 코드

Exploring the Impact of the Output Format on the Evaluation of Large Language Models for Code Translation

https://github.com/rizwan09/redcoder

공식 코드

Retrieval Augmented Code Generation and Summarization

https://github.com/rshin/seq2struct

공식 코드

Program Synthesis and Semantic Parsing with Learned Code Idioms

https://github.com/rufimelo99/SAE-Java-Bug-Detection

공식 코드

Are Sparse Autoencoders Useful for Java Function Bug Detection?

https://github.com/ruili33/sec

공식 코드

Are Human-generated Demonstrations Necessary for In-context Learning?

https://github.com/ruiqi-zhong/SemanticScaffold

공식 코드

Semantic Scaffolds for Pseudocode-to-Code Generation

https://github.com/rutatang/hygenar

공식 코드

HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation

https://github.com/s2e-lab/llm-education-survey

공식 코드

Large Language Models in Computer Science Education: A Systematic Literature Review

https://github.com/sade-adrien/stelocoder

공식 코드

SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation

https://github.com/safeailab/eagle

공식 코드

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

https://github.com/saikat107/natgen

공식 코드

NatGen: Generative pre-training by "Naturalizing" source code

https://github.com/sailresearch/fmse-blogs

공식 코드

Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models

https://github.com/salesforce/CodeGen

공식 코드

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

https://github.com/salesforce/WikiSQL

공식 코드

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

https://github.com/salesforce/coderl

공식 코드

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

https://github.com/salesforce/codet5

공식 코드

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

https://github.com/salesforce/jaxformer

공식 코드

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

https://github.com/salesforceairesearch/jetts-benchmark

공식 코드

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators

https://github.com/salokr/propmted

공식 코드

Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance

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