nju-websoft / DraCo
Dataflow-guided retrieval augmentation for repository-level code completion, ACL 2024 (main)
☆22Updated 9 months ago
Alternatives and similar repositories for DraCo:
Users that are interested in DraCo are comparing it to the libraries listed below
- ☆31Updated 8 months ago
- An Evolving Code Generation Benchmark Aligned with Real-world Code Repositories☆52Updated 6 months ago
- CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context☆12Updated 4 months ago
- Dianshu-Liao / AAA-Code-Generation-Framework-for-Code-Repository-Local-Aware-Global-Aware-Third-Party-Aware☆18Updated last year
- Reinforcement Learning for Repository-Level Code Completion☆24Updated 6 months ago
- This repo illustrates how to evaluate the artifacts in the paper An Extensive Study on Pre-trained Models for Program Understanding and G…☆25Updated 2 years ago
- ☆22Updated 5 months ago
- Benchmark ClassEval for class-level code generation.☆135Updated 4 months ago
- Repo-Level Code generation papers☆146Updated last week
- ☆46Updated 2 years ago
- This repo is for our submission for ICSE 2025.☆20Updated 9 months ago
- Artifact repository for the paper "Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code", In P…☆43Updated 9 months ago
- Code and data for XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence☆68Updated last month
- ☆20Updated 7 months ago
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)☆133Updated 7 months ago
- Pip compatible CodeBLEU metric implementation available for linux/macos/win☆80Updated last week
- Source Code Data Augmentation for Deep Learning: A Survey.☆64Updated 8 months ago
- Developer-Intent Driven Code Comment Generation☆16Updated 2 years ago
- This is the official implement for the paper 'Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases''☆13Updated last year
- ☆1Updated last year
- The repository for paper "DebugBench: "Evaluating Debugging Capability of Large Language Models".☆66Updated 8 months ago
- [LREC-COLING'24] HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization☆35Updated this week
- ☆11Updated last year
- For our ICSE23 paper "Impact of Code Language Models on Automated Program Repair" by Nan Jiang, Kevin Liu, Thibaud Lutellier, and Lin Tan☆59Updated 4 months ago
- A collection of practical code generation tasks and tests in open source projects. Complementary to HumanEval by OpenAI.☆134Updated 2 months ago
- Source Code for Paper "Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning"☆15Updated last year
- ✅SRepair: Powerful LLM-based Program Repairer with $0.029/Fixed Bug☆57Updated 10 months ago
- ☆18Updated 3 months ago
- Source codes for paper ”ReACC: A Retrieval-Augmented Code Completion Framework“☆62Updated 2 years ago
- Official implementation of our ICSE 2023 paper on Automatic Code Generation.☆27Updated last year