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

@ -85,12 +85,12 @@ def test_spiral_matrix_answer():
# Score answer in list format (partially correct)
entry = {"answer": "1 2 3 6 9 8 7 4 5"}
answer = "[1, 2, 3, 6, 9, 8, 7, 4, 5]"
assert dataset.score_answer(answer, entry) == 0.5
assert dataset.score_answer(answer, entry) == 0.1
# Answer is incorrect
entry = {"answer": "1 2 3 6 9 8 7 4 5"}
answer = "1 2 3"
assert dataset.score_answer(answer, entry) == 0.01
assert dataset.score_answer(answer, entry) == 0.0
# Answer is none
entry = {"answer": "1 2 3 6 9 8 7 4 5"}