Minor question template & score_answer improvements (#261)

* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
This commit is contained in:
Andreas Köpf 2025-03-04 21:55:09 +01:00 committed by GitHub
parent 061282e373
commit 5d7fbac0ad
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
106 changed files with 403 additions and 507 deletions

View file

@ -103,6 +103,10 @@ class ComplexArithmeticDataset(ProceduralDataset):
# Normalize the answer string by removing spaces and converting to lowercase
answer = answer.replace(" ", "").lower()
# remove brackets
while len(answer) > 1 and answer[0] == "(" and answer[-1] == ")":
answer = answer[1:-1]
# Convert mathematical notation 'i' to Python's 'j' for complex numbers
answer = answer.replace("i", "j")