RNAQwen / reports /eval_selfcheck.json
RomanCohort's picture
add reports/eval_selfcheck.json
d2cf2a2 verified
Raw History Blame Contribute Delete
2.83 kB
{
"embedder": "bert",
"A_rouge_parity": {
"available": true,
"cases": [
{
"case": "identical",
"ours": {
"rouge1": 1.0,
"rouge2": 1.0,
"rougeL": 1.0
},
"rouge_score": {
"rouge1": 1.0,
"rouge2": 1.0,
"rougeL": 1.0
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "paraphrase",
"ours": {
"rouge1": 0.6666666666666666,
"rouge2": 0.3283582089552239,
"rougeL": 0.46376811594202894
},
"rouge_score": {
"rouge1": 0.6666666666666666,
"rouge2": 0.3283582089552239,
"rougeL": 0.46376811594202894
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "partial",
"ours": {
"rouge1": 0.47058823529411764,
"rouge2": 0.326530612244898,
"rougeL": 0.47058823529411764
},
"rouge_score": {
"rouge1": 0.47058823529411764,
"rouge2": 0.326530612244898,
"rougeL": 0.47058823529411764
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "unrelated",
"ours": {
"rouge1": 0.10714285714285714,
"rouge2": 0.0,
"rougeL": 0.10714285714285714
},
"rouge_score": {
"rouge1": 0.10714285714285714,
"rouge2": 0.0,
"rougeL": 0.10714285714285714
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "empty",
"ours": {
"rouge1": 0.0,
"rouge2": 0.0,
"rougeL": 0.0
},
"rouge_score": {
"rouge1": 0.0,
"rouge2": 0.0,
"rougeL": 0
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "punctuation",
"ours": {
"rouge1": 0.34782608695652173,
"rouge2": 0.3181818181818182,
"rougeL": 0.34782608695652173
},
"rouge_score": {
"rouge1": 0.34782608695652173,
"rouge2": 0.3181818181818182,
"rougeL": 0.34782608695652173
},
"max_abs_diff": 0.0,
"ok": true
},
{
"case": "numbers",
"ours": {
"rouge1": 0.8750000000000001,
"rouge2": 0.8571428571428571,
"rougeL": 0.8750000000000001
},
"rouge_score": {
"rouge1": 0.8750000000000001,
"rouge2": 0.8571428571428571,
"rougeL": 0.8750000000000001
},
"max_abs_diff": 0.0,
"ok": true
}
],
"max_abs_diff": 0.0,
"passed": true
}
}