DiplomovaPraca/outputs/ragas_pilot/scores.csv

202 lines
13 KiB
Plaintext

case_id,mode,metric,status,value,reason,seconds
indication-01,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
indication-01,bypass,context_recall,skipped,,no_retrieval_in_baseline,
contraindication-01,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
contraindication-01,bypass,context_recall,skipped,,no_retrieval_in_baseline,
interaction-01,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
interaction-01,bypass,context_recall,skipped,,no_retrieval_in_baseline,
warning-01,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
warning-01,bypass,context_recall,skipped,,no_retrieval_in_baseline,
unanswerable-01,mix,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,mix,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,mix,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,mix,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,bypass,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,bypass,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,bypass,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,bypass,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,naive,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,naive,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,naive,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,naive,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,local,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,local,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,local,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,local,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,hybrid,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,hybrid,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,hybrid,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-01,hybrid,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
indication-02,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
indication-02,bypass,context_recall,skipped,,no_retrieval_in_baseline,
contraindication-02,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
contraindication-02,bypass,context_recall,skipped,,no_retrieval_in_baseline,
interaction-02,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
interaction-02,bypass,context_recall,skipped,,no_retrieval_in_baseline,
warning-02,bypass,faithfulness,skipped,,no_retrieval_in_baseline,
warning-02,bypass,context_recall,skipped,,no_retrieval_in_baseline,
unanswerable-02,mix,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,mix,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,mix,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,mix,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,bypass,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,bypass,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,bypass,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,bypass,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,naive,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,naive,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,naive,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,naive,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,local,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,local,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,local,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,local,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,hybrid,faithfulness,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,hybrid,answer_relevancy,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,hybrid,context_recall,skipped,,abstention_scenario_evaluated_separately,
unanswerable-02,hybrid,answer_correctness,skipped,,abstention_scenario_evaluated_separately,
indication-01,bypass,answer_relevancy,ok,0.8336740450428343,,2.302
indication-01,naive,answer_relevancy,ok,0.8413767093812826,,1.843
indication-01,naive,context_recall,ok,1.0,,4.089
indication-01,naive,faithfulness,ok,0.8181818181818182,,12.633
indication-01,naive,answer_correctness,ok,0.8426211342298708,,12.218
indication-01,local,answer_relevancy,ok,0.8146961312204395,,1.969
indication-01,local,context_recall,ok,1.0,,4.755
indication-01,bypass,answer_correctness,ok,0.39040561850206995,,33.67
indication-01,local,faithfulness,ok,0.6666666666666666,,26.284
indication-01,hybrid,answer_relevancy,ok,0.8659158503650933,,1.996
indication-01,hybrid,context_recall,ok,0.8,,5.127
indication-01,local,answer_correctness,ok,0.8154786680797599,,22.987
indication-01,hybrid,faithfulness,ok,1.0,,16.57
indication-01,mix,answer_relevancy,ok,0.8382869190155958,,2.085
indication-01,mix,context_recall,ok,0.8,,5.266
indication-01,hybrid,answer_correctness,ok,0.7102264898222257,,17.531
contraindication-01,naive,faithfulness,ok,1.0,,13.677
contraindication-01,naive,answer_relevancy,ok,0.5487599361226743,,1.943
contraindication-01,naive,context_recall,ok,0.0,,7.986
indication-01,mix,answer_correctness,ok,0.4466746717575326,,40.178
indication-01,mix,faithfulness,ok,0.8648648648648649,,47.779
contraindication-01,local,answer_relevancy,ok,0.0,,1.888
contraindication-01,local,context_recall,ok,0.0,,7.427
contraindication-01,naive,answer_correctness,ok,0.3400720301177152,,23.647
contraindication-01,local,faithfulness,ok,0.9411764705882353,,20.95
contraindication-01,hybrid,answer_relevancy,ok,0.6246234588792787,,2.554
contraindication-01,hybrid,context_recall,ok,0.0,,7.684
contraindication-01,local,answer_correctness,ok,0.11085266569327383,,34.453
contraindication-01,hybrid,faithfulness,ok,0.8461538461538461,,34.399
contraindication-01,mix,answer_relevancy,ok,0.0,,1.963
contraindication-01,mix,faithfulness,ok,0.2857142857142857,,10.903
contraindication-01,mix,context_recall,ok,0.0,,6.99
contraindication-01,bypass,answer_relevancy,ok,0.3085577488833277,,2.06
contraindication-01,hybrid,answer_correctness,ok,0.3488431436528561,,41.511
contraindication-01,mix,answer_correctness,ok,0.1152586673093139,,26.242
interaction-01,local,answer_relevancy,ok,0.6704921383309878,,1.667
interaction-01,local,faithfulness,ok,0.4117647058823529,,17.061
interaction-01,local,context_recall,ok,0.0,,7.623
interaction-01,hybrid,faithfulness,ok,0.2,,12.766
interaction-01,hybrid,answer_relevancy,ok,0.7215157470632865,,1.672
contraindication-01,bypass,answer_correctness,ok,0.3409825829291848,,48.681
interaction-01,hybrid,context_recall,ok,0.0,,10.94
interaction-01,local,answer_correctness,ok,0.3842396956036642,,33.411
interaction-01,mix,answer_relevancy,ok,0.8730483526432252,,1.596
interaction-01,mix,faithfulness,ok,0.6666666666666666,,14.476
interaction-01,mix,context_recall,ok,0.0,,6.823
interaction-01,bypass,answer_relevancy,ok,0.7413059826251285,,1.913
interaction-01,hybrid,answer_correctness,ok,0.413744114376974,,36.867
interaction-01,mix,answer_correctness,ok,0.2802822778088285,,27.753
interaction-01,naive,answer_relevancy,ok,0.8172116514177749,,1.573
interaction-01,naive,faithfulness,ok,0.9375,,22.14
interaction-01,naive,context_recall,ok,0.0,,9.056
interaction-01,bypass,answer_correctness,ok,0.37156297641415215,,50.306
warning-01,hybrid,answer_relevancy,ok,0.0,,3.699
warning-01,hybrid,context_recall,ok,0.0,,5.158
warning-01,mix,answer_relevancy,ok,0.0,,2.651
warning-01,mix,context_recall,ok,0.6666666666666666,,6.37
warning-01,bypass,answer_relevancy,ok,0.7047779318608279,,2.714
warning-01,hybrid,answer_correctness,ok,0.0810195024746072,,24.736
warning-01,hybrid,faithfulness,ok,0.5882352941176471,,26.359
warning-01,naive,answer_relevancy,ok,0.0,,2.696
warning-01,mix,faithfulness,ok,1.0,,31.472
warning-01,naive,context_recall,ok,0.0,,5.802
warning-01,naive,faithfulness,ok,1.0,,14.832
warning-01,local,answer_relevancy,ok,0.0,,2.868
warning-01,naive,answer_correctness,ok,0.10641080113869646,,14.807
warning-01,local,context_recall,ok,1.0,,4.366
indication-02,bypass,answer_relevancy,ok,0.7110334196766454,,2.434
warning-01,mix,answer_correctness,ok,0.35135213308585866,,47.174
warning-01,local,faithfulness,ok,0.6153846153846154,,22.224
indication-02,naive,answer_relevancy,ok,0.7790697639822254,,2.969
indication-02,naive,context_recall,ok,1.0,,8.762
warning-01,local,answer_correctness,ok,0.12249738361039147,,24.229
interaction-01,naive,answer_correctness,ok,0.5550557834340627,,71.67
indication-02,naive,faithfulness,ok,1.0,,19.063
indication-02,local,answer_relevancy,ok,0.9688923114258469,,2.668
indication-02,local,context_recall,ok,0.8888888888888888,,9.624
indication-02,local,faithfulness,ok,1.0,,19.292
indication-02,hybrid,answer_relevancy,ok,0.8459087552785475,,2.298
indication-02,naive,answer_correctness,ok,0.879525351297198,,27.066
indication-02,hybrid,context_recall,ok,1.0,,8.1
indication-02,hybrid,faithfulness,ok,0.9166666666666666,,18.608
indication-02,mix,answer_relevancy,ok,0.8045249582593978,,2.342
indication-02,local,answer_correctness,ok,0.7906915876312732,,29.27
indication-02,bypass,answer_correctness,ok,0.886151131659857,,54.4
indication-02,mix,context_recall,ok,0.8888888888888888,,10.271
contraindication-02,naive,answer_relevancy,ok,0.7163312111885355,,2.235
indication-02,hybrid,answer_correctness,ok,0.8459444357354957,,23.328
contraindication-02,naive,context_recall,ok,0.0,,4.685
contraindication-02,naive,faithfulness,ok,1.0,,27.572
indication-02,mix,faithfulness,ok,1.0,,31.836
contraindication-02,local,answer_relevancy,ok,0.6760947364274177,,2.845
contraindication-02,local,context_recall,ok,0.0,,4.498
indication-02,mix,answer_correctness,ok,0.5844439754447375,,35.166
contraindication-02,hybrid,answer_relevancy,ok,0.0,,2.242
contraindication-02,naive,answer_correctness,ok,0.14184780773802788,,23.373
contraindication-02,hybrid,context_recall,ok,0.0,,4.848
contraindication-02,hybrid,faithfulness,ok,0.8181818181818182,,18.945
contraindication-02,mix,answer_relevancy,ok,0.7770866813218135,,2.263
contraindication-02,local,faithfulness,ok,0.7692307692307693,,40.044
contraindication-02,mix,context_recall,ok,1.0,,3.572
contraindication-02,hybrid,answer_correctness,ok,0.13751662015143826,,20.615
contraindication-02,bypass,answer_relevancy,ok,0.5651220185561544,,2.353
contraindication-02,local,answer_correctness,ok,0.18701431227692278,,37.011
interaction-02,local,answer_relevancy,ok,0.33274921354883763,,1.796
contraindication-02,mix,faithfulness,ok,0.7857142857142857,,29.059
interaction-02,local,context_recall,ok,0.0,,4.938
contraindication-02,mix,answer_correctness,ok,0.5283169073938874,,19.373
interaction-02,hybrid,answer_relevancy,ok,0.710010688080564,,1.869
interaction-02,local,faithfulness,ok,0.21428571428571427,,20.394
interaction-02,hybrid,context_recall,ok,0.3333333333333333,,6.403
interaction-02,hybrid,faithfulness,ok,0.7142857142857143,,16.228
warning-01,bypass,answer_correctness,ok,0.17177298311723022,,41.639
interaction-02,mix,answer_relevancy,ok,0.7155466059400872,,2.491
interaction-02,mix,context_recall,ok,0.0,,8.913
interaction-02,bypass,answer_relevancy,ok,0.5252403367666899,,2.704
interaction-02,mix,faithfulness,ok,0.8,,18.739
interaction-02,local,answer_correctness,ok,0.43050382103090135,,34.41
interaction-02,hybrid,answer_correctness,ok,0.2305346007015037,,25.879
interaction-02,naive,answer_relevancy,ok,0.0,,3.255
interaction-02,naive,context_recall,ok,0.0,,5.051
contraindication-02,bypass,answer_correctness,ok,0.28961073692570205,,56.977
interaction-02,naive,faithfulness,ok,0.875,,14.994
warning-02,hybrid,answer_relevancy,ok,0.0,,2.724
interaction-02,mix,answer_correctness,ok,0.6269070092994843,,29.494
warning-02,hybrid,faithfulness,ok,0.7777777777777778,,13.601
warning-02,mix,answer_relevancy,ok,0.8873992619846888,,2.146
warning-02,hybrid,context_recall,ok,0.0,,12.75
interaction-02,naive,answer_correctness,ok,0.14279842390947706,,24.042
warning-02,bypass,answer_relevancy,ok,0.6650156269431805,,2.065
warning-02,mix,faithfulness,ok,1.0,,17.416
warning-02,mix,context_recall,ok,0.36363636363636365,,13.192
warning-02,naive,answer_relevancy,ok,0.8354692338835598,,2.499
interaction-02,bypass,answer_correctness,ok,0.36896249546678567,,52.856
warning-02,naive,faithfulness,ok,1.0,,16.66
warning-02,naive,context_recall,ok,0.3333333333333333,,13.939
warning-02,local,answer_relevancy,ok,0.553480461774667,,1.6
warning-02,hybrid,answer_correctness,ok,0.11460890995058678,,40.771
warning-02,mix,answer_correctness,ok,0.5346924251233847,,39.149
warning-02,local,context_recall,ok,0.0,,12.394
warning-02,local,faithfulness,ok,0.8666666666666667,,21.547
warning-02,naive,answer_correctness,ok,0.5208708409607992,,30.929
warning-02,local,answer_correctness,ok,0.10882217571332953,,34.551
warning-02,bypass,answer_correctness,ok,0.42470478380505927,,61.649