Spaces:
Running
Running
ashe0042 commited on
Commit ·
56004c5
1
Parent(s): 906ab20
Add benchmark results for dashboard deployment
Browse files- results/raw_results.jsonl +0 -0
- results/summary.json +42 -0
results/raw_results.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
results/summary.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"naive": {
|
| 3 |
+
"total": 119,
|
| 4 |
+
"correct_and_faithful": 91,
|
| 5 |
+
"fabricated_citation": 0,
|
| 6 |
+
"misstated_obligation": 16,
|
| 7 |
+
"missing_citation": 8,
|
| 8 |
+
"real_but_irrelevant": 4
|
| 9 |
+
},
|
| 10 |
+
"hybrid": {
|
| 11 |
+
"total": 119,
|
| 12 |
+
"correct_and_faithful": 96,
|
| 13 |
+
"fabricated_citation": 0,
|
| 14 |
+
"misstated_obligation": 13,
|
| 15 |
+
"missing_citation": 5,
|
| 16 |
+
"real_but_irrelevant": 5
|
| 17 |
+
},
|
| 18 |
+
"rerank": {
|
| 19 |
+
"total": 119,
|
| 20 |
+
"correct_and_faithful": 95,
|
| 21 |
+
"fabricated_citation": 1,
|
| 22 |
+
"misstated_obligation": 14,
|
| 23 |
+
"missing_citation": 5,
|
| 24 |
+
"real_but_irrelevant": 4
|
| 25 |
+
},
|
| 26 |
+
"kg_augmented": {
|
| 27 |
+
"total": 119,
|
| 28 |
+
"correct_and_faithful": 91,
|
| 29 |
+
"fabricated_citation": 0,
|
| 30 |
+
"misstated_obligation": 14,
|
| 31 |
+
"missing_citation": 8,
|
| 32 |
+
"real_but_irrelevant": 6
|
| 33 |
+
},
|
| 34 |
+
"grounded": {
|
| 35 |
+
"total": 119,
|
| 36 |
+
"correct_and_faithful": 105,
|
| 37 |
+
"fabricated_citation": 0,
|
| 38 |
+
"misstated_obligation": 7,
|
| 39 |
+
"missing_citation": 5,
|
| 40 |
+
"real_but_irrelevant": 2
|
| 41 |
+
}
|
| 42 |
+
}
|