Skip to content

Incorrect requirement in humaneval shows the data leakage in model #25

@feixiangdejiahao

Description

@feixiangdejiahao

Humaneval/163

def generate_integers(a, b):
"""
Given two positive integers a and b, return the even digits between a
and b, in ascending order.

For example:
generate_integers(2, 8) => [2, 4, 6, 8]
generate_integers(8, 2) => [2, 4, 6, 8]
generate_integers(10, 14) => []
"""

Based on the example, I can not understand the requirement. When I check the reference solution, I am shocked.

def generate_integers(a, b):
    lower = max(2, min(a, b))
    upper = min(8, max(a, b))

    return [i for i in range(lower, upper+1) if i % 2 == 0]

But my experiment shows that the original pass1 is 0.099. From my understanding, it comes from data leakage since I can't imagine how model can solve this problem.
Here is the passed program:

from typing import List

def generate_integers(a: int, b: int) -> List[int]:
    start = min(a, b)
    end = max(a, b)
    result = [num for num in range(start, end + 1) if num % 2 == 0 and num in {2, 4, 6, 8}]
    return sorted(result)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions