MBPP-ET
Emerging4papers using it
2023first seen
The 'MBPP-ET' dataset/benchmark contains a collection of programming tasks designed to evaluate the effectiveness of code generation techniques, particularly in the context of modularized reasoning and hierarchical problem-solving.
Papers using MBPP-ET (4)
- Modularization is Better: Effective Code Generation with Modular
PromptingCodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code GenerationSOEN-101: Code Generation by Emulating Software Process Models Using
Large Language Model AgentsClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification