pecc-leaderboard / text.py
Patrick Haller
Update
08cfea7
raw
history blame
1.28 kB
TITLE_TEXT = "PECC - Problem Extraction and Coding Challenges Evaluation Benchmark"
INTRODUCTION_TEXT = """πŸ“„ PECC: An extensive benchmark centered on code generation from narrative-embedded problem descriptions. Unlike prior benchmarks that evaluate code generation using specific instructions, our dataset requires models to comprehend, extract requirements, and produce the essential code for problem-solving. This approach necessitates syntactically accurate programs and demands reading comprehension skills to derive the desired solution."""
TASK_DESCRIPTION = """## Task Description
The task for the model is to generate directly executable python code.
### Instruction
The model is first prompted with a system prompt, which is a short description of the problem. The model is then asked to generate the python code that solves the problem.
### Task
The model receives the task itself.
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite our paper"
CITATION_BUTTON_TEXT = r"""
Coming soon!
"""
# @misc{pecc,
# author = {Patrick Haller and Jonas Golde and Alan Akbik},
# title = {PECC - Problem Extraction and Coding Challenges},
# year = {2024},
# publisher = {GitHub},
# journal = {GitHub repository},
# howpublished = {}
# }