152 lines
3.0 KiB
JSON
152 lines
3.0 KiB
JSON
{
|
|
"bypass": {
|
|
"faithfulness": {
|
|
"mean": null,
|
|
"n_ok": 0,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 10
|
|
},
|
|
"context_recall": {
|
|
"mean": null,
|
|
"n_ok": 0,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 10
|
|
},
|
|
"answer_relevancy": {
|
|
"mean": 0.6318408887943485,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_correctness": {
|
|
"mean": 0.4055191636025052,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
}
|
|
},
|
|
"mix": {
|
|
"faithfulness": {
|
|
"mean": 0.8003700128700129,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_relevancy": {
|
|
"mean": 0.611986597395601,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"context_recall": {
|
|
"mean": 0.4648989898989899,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_correctness": {
|
|
"mean": 0.4334910084028784,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
}
|
|
},
|
|
"naive": {
|
|
"faithfulness": {
|
|
"mean": 0.9538352272727273,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_relevancy": {
|
|
"mean": 0.5672773132470066,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"context_recall": {
|
|
"mean": 0.2916666666666667,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_correctness": {
|
|
"mean": 0.4411502716032309,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
}
|
|
},
|
|
"local": {
|
|
"faithfulness": {
|
|
"mean": 0.6856469510881276,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_relevancy": {
|
|
"mean": 0.5020506240910245,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"context_recall": {
|
|
"mean": 0.3611111111111111,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_correctness": {
|
|
"mean": 0.3687625387049395,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
}
|
|
},
|
|
"hybrid": {
|
|
"faithfulness": {
|
|
"mean": 0.7326626396479338,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_relevancy": {
|
|
"mean": 0.47099681245834624,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"context_recall": {
|
|
"mean": 0.26666666666666666,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
},
|
|
"answer_correctness": {
|
|
"mean": 0.36030472710821093,
|
|
"n_ok": 8,
|
|
"n_error": 0,
|
|
"n_undefined": 0,
|
|
"n_skipped": 2
|
|
}
|
|
}
|
|
} |