Skip to content

fixed mmmu by cooking options from answer, when options is not given in the instance #1921

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fixed mmmu by cooking options from answer, when options is not given in the instance #1921

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ac20949
fixed mmmu by necessary filters
dafnapension Aug 20, 2025
2701950
cook options when empty rather than filter out
dafnapension Aug 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 16 additions & 2 deletions prepare/cards/mmmu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,11 @@
from unitxt.blocks import LoadHF, TaskCard
from unitxt.catalog import add_to_catalog
from unitxt.collections_operators import Filter
from unitxt.operators import ListFieldValues, MapValues
from unitxt.operators import (
ExecuteExpression,
ListFieldValues,
MapValues,
)
from unitxt.processors import LiteralEval, Lower
from unitxt.splitters import RenameSplits
from unitxt.string_operators import MapReplace
Expand Down Expand Up @@ -40,6 +44,8 @@
"Sociology",
]

mapping = {"A": 0, "B": 1, "C": 2, "D": 3, "E": 4, "F": 5, "G": 6, "H": 7, "I": 8}

for name in config_names:
card = TaskCard(
loader=LoadHF(
Expand All @@ -51,6 +57,14 @@
fields=[f"image_{i}" for i in range(1, 8)], to_field="media/images"
),
Filter(field="media/images", values=[None]),
ExecuteExpression(
expression="options if options != '[]' else '[\"'+answer+'\"]'",
to_field="options",
),
ExecuteExpression(
expression="'A' if options == '[\"'+answer+'\"]' else answer",
to_field="answer",
),
MapReplace(
field_to_field={"question": "question", "options": "choices"},
mapping={
Expand All @@ -62,7 +76,7 @@
Lower(field="subfield", to_field="topic"),
MapValues(
field="answer",
mapping={"A": 0, "B": 1, "C": 2, "D": 3, "E": 4, "?": None},
mapping=mapping,
),
],
task="tasks.qa.multiple_choice.with_topic",
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/accounting.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/agriculture.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/architecture_and_engineering.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/art.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/art_theory.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/basic_medical_science.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/biology.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/chemistry.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/clinical_medicine.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/computer_science.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/design.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
15 changes: 14 additions & 1 deletion src/unitxt/catalog/cards/mmmu/diagnostics_and_laboratory_medicine.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,16 @@
null
]
},
{
"__type__": "execute_expression",
"expression": "options if options != '[]' else '[\"'+answer+'\"]'",
"to_field": "options"
},
{
"__type__": "execute_expression",
"expression": "'A' if options == '[\"'+answer+'\"]' else answer",
"to_field": "answer"
},
{
"__type__": "map_replace",
"field_to_field": {
Expand Down Expand Up @@ -70,7 +80,10 @@
"C": 2,
"D": 3,
"E": 4,
"?": null
"F": 5,
"G": 6,
"H": 7,
"I": 8
}
}
],
Expand Down
Loading