Collections of research, benchmarks and tools towards more robust and reliable language models for code; LM4Code; LM4SE; reliable LLM; LLM4Code

✅SRepair: Powerful LLM-based Program Repairer with $0.029/Fixed Bug

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

Code for ACL (main) paper "JumpCoder: Go Beyond Autoregressive Coder via Online Modification"

Indexing three datasets for GPTScan

[NeurIPS'24] Fully Transparent Self-Alignment for Code Generation

A curated list of papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering

The official code of the paper "InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct"(https://arxiv.org/abs/2407.05700).

For paper "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" by Danning Xie, Zhuo Zhang, Nan Jiang, Xiangzhe Xu, Lin Tan, and Xiangyu Zhang. Accepted by ACM CCS 2024. 🏆 ACM SIGSAC Distinguished Paper Award Winner

Journey to the WEST (trustWorthy intElligent Software developmenT)

MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for LLMs.