kbl/benchmark_statistic.json
2025-10-31 13:19:00 +09:00

104 lines
2.2 KiB
JSON

[
{
"doc-id": 1,
"subset": "knowledge",
"doc-name": "kbl_legal_common_legal_mistake_qa_reasoning_v0.1",
"counts": {
"total": 40,
"A": 13,
"B": 13,
"C": 14
}
},
{
"doc-id": 2,
"subset": "knowledge",
"doc-name": "kbl_legal_common_legal_mistake_qa_v0.1",
"counts": {
"total": 41,
"A": 13,
"B": 14,
"C": 14
}
},
{
"doc-id": 3,
"subset": "knowledge",
"doc-name": "kbl_legal_concept_qa_v0.1",
"counts": {
"total": 100,
"A": 20,
"B": 20,
"C": 20,
"D": 20,
"E": 20
}
},
{
"doc-id": 4,
"subset": "knowledge",
"doc-name": "kbl_offense_component_qa_v0.1",
"counts": {
"total": 102,
"A": 51,
"B": 51
}
},
{
"doc-id": 5,
"subset": "knowledge",
"doc-name": "kbl_query_and_statute_matching_qa_v0.1",
"counts": {
"total": 52,
"A": 11,
"B": 10,
"C": 10,
"D": 10,
"E": 11
}
},
{
"doc-id": 6,
"subset": "knowledge",
"doc-name": "kbl_statute_number_and_content_matching_qa_v0.1",
"counts": {
"total": 100,
"A": 20,
"B": 20,
"C": 20,
"D": 20
}
},
{
"doc-id": 7,
"subset": "knowledge",
"doc-name": "kbl_statute_hallucination_qa_v0.1",
"counts": {
"total": 75,
"A": 19,
"B": 19,
"C": 19,
"D": 18
}
},
{
"doc-id": 9,
"subset": "reasoning",
"doc-name": "kbl_causal_reasoning_qa_v0.1",
"counts": {
"total": 95,
"A": 47,
"B": 48
}
},
{
"doc-id": 10,
"subset": "reasoning",
"doc-name": "kbl_logical_contradiction_qa_v0.1",
"counts": {
"total": 91,
"A": 46,
"B": 45
}
}
]