task_no |
task_name |
score |
qa1 |
single-supporting-fact |
100 |
qa2 |
two-supporting-facts |
99.4 |
qa3 |
three-supporting-facts |
62.0 |
qa4 |
two-arg-relations |
100 |
qa5 |
three-arg-relations |
96.0 |
qa6 |
yes-no-questions |
100 |
qa7 |
counting |
100 |
qa8 |
lists-sets |
95.6 |
qa9 |
simple-negation |
100 |
qa10 |
indefinite-knowledge |
100 |
qa11 |
basic-coreference |
100 |
qa12 |
conjunction |
100 |
qa13 |
compound-coreference |
100 |
qa14 |
time-reasoning |
100 |
qa15 |
basic-deduction |
100 |
qa16 |
basic-induction |
100 |
qa17 |
positional-reasoning |
100 |
qa18 |
size-reasoning |
100 |
qa19 |
path-finding |
100 |
qa20 |
agents-motivations |
100 |
INPUT_TEMPLATE = """
Context:
{context}
Question:
{question}
Answer:
{answer}
"""
input_text = INPUT_TEMPLATE.format_map({
"context":context,
"question":question,
"answer":answer
}).strip()