DiplomovaPraca/outputs/ragas_pilot/scores.csv

13 KiB

1case_idmodemetricstatusvaluereasonseconds
2indication-01bypassfaithfulnessskippedno_retrieval_in_baseline
3indication-01bypasscontext_recallskippedno_retrieval_in_baseline
4contraindication-01bypassfaithfulnessskippedno_retrieval_in_baseline
5contraindication-01bypasscontext_recallskippedno_retrieval_in_baseline
6interaction-01bypassfaithfulnessskippedno_retrieval_in_baseline
7interaction-01bypasscontext_recallskippedno_retrieval_in_baseline
8warning-01bypassfaithfulnessskippedno_retrieval_in_baseline
9warning-01bypasscontext_recallskippedno_retrieval_in_baseline
10unanswerable-01mixfaithfulnessskippedabstention_scenario_evaluated_separately
11unanswerable-01mixanswer_relevancyskippedabstention_scenario_evaluated_separately
12unanswerable-01mixcontext_recallskippedabstention_scenario_evaluated_separately
13unanswerable-01mixanswer_correctnessskippedabstention_scenario_evaluated_separately
14unanswerable-01bypassfaithfulnessskippedabstention_scenario_evaluated_separately
15unanswerable-01bypassanswer_relevancyskippedabstention_scenario_evaluated_separately
16unanswerable-01bypasscontext_recallskippedabstention_scenario_evaluated_separately
17unanswerable-01bypassanswer_correctnessskippedabstention_scenario_evaluated_separately
18unanswerable-01naivefaithfulnessskippedabstention_scenario_evaluated_separately
19unanswerable-01naiveanswer_relevancyskippedabstention_scenario_evaluated_separately
20unanswerable-01naivecontext_recallskippedabstention_scenario_evaluated_separately
21unanswerable-01naiveanswer_correctnessskippedabstention_scenario_evaluated_separately
22unanswerable-01localfaithfulnessskippedabstention_scenario_evaluated_separately
23unanswerable-01localanswer_relevancyskippedabstention_scenario_evaluated_separately
24unanswerable-01localcontext_recallskippedabstention_scenario_evaluated_separately
25unanswerable-01localanswer_correctnessskippedabstention_scenario_evaluated_separately
26unanswerable-01hybridfaithfulnessskippedabstention_scenario_evaluated_separately
27unanswerable-01hybridanswer_relevancyskippedabstention_scenario_evaluated_separately
28unanswerable-01hybridcontext_recallskippedabstention_scenario_evaluated_separately
29unanswerable-01hybridanswer_correctnessskippedabstention_scenario_evaluated_separately
30indication-02bypassfaithfulnessskippedno_retrieval_in_baseline
31indication-02bypasscontext_recallskippedno_retrieval_in_baseline
32contraindication-02bypassfaithfulnessskippedno_retrieval_in_baseline
33contraindication-02bypasscontext_recallskippedno_retrieval_in_baseline
34interaction-02bypassfaithfulnessskippedno_retrieval_in_baseline
35interaction-02bypasscontext_recallskippedno_retrieval_in_baseline
36warning-02bypassfaithfulnessskippedno_retrieval_in_baseline
37warning-02bypasscontext_recallskippedno_retrieval_in_baseline
38unanswerable-02mixfaithfulnessskippedabstention_scenario_evaluated_separately
39unanswerable-02mixanswer_relevancyskippedabstention_scenario_evaluated_separately
40unanswerable-02mixcontext_recallskippedabstention_scenario_evaluated_separately
41unanswerable-02mixanswer_correctnessskippedabstention_scenario_evaluated_separately
42unanswerable-02bypassfaithfulnessskippedabstention_scenario_evaluated_separately
43unanswerable-02bypassanswer_relevancyskippedabstention_scenario_evaluated_separately
44unanswerable-02bypasscontext_recallskippedabstention_scenario_evaluated_separately
45unanswerable-02bypassanswer_correctnessskippedabstention_scenario_evaluated_separately
46unanswerable-02naivefaithfulnessskippedabstention_scenario_evaluated_separately
47unanswerable-02naiveanswer_relevancyskippedabstention_scenario_evaluated_separately
48unanswerable-02naivecontext_recallskippedabstention_scenario_evaluated_separately
49unanswerable-02naiveanswer_correctnessskippedabstention_scenario_evaluated_separately
50unanswerable-02localfaithfulnessskippedabstention_scenario_evaluated_separately
51unanswerable-02localanswer_relevancyskippedabstention_scenario_evaluated_separately
52unanswerable-02localcontext_recallskippedabstention_scenario_evaluated_separately
53unanswerable-02localanswer_correctnessskippedabstention_scenario_evaluated_separately
54unanswerable-02hybridfaithfulnessskippedabstention_scenario_evaluated_separately
55unanswerable-02hybridanswer_relevancyskippedabstention_scenario_evaluated_separately
56unanswerable-02hybridcontext_recallskippedabstention_scenario_evaluated_separately
57unanswerable-02hybridanswer_correctnessskippedabstention_scenario_evaluated_separately
58indication-01bypassanswer_relevancyok0.83367404504283432.302
59indication-01naiveanswer_relevancyok0.84137670938128261.843
60indication-01naivecontext_recallok1.04.089
61indication-01naivefaithfulnessok0.818181818181818212.633
62indication-01naiveanswer_correctnessok0.842621134229870812.218
63indication-01localanswer_relevancyok0.81469613122043951.969
64indication-01localcontext_recallok1.04.755
65indication-01bypassanswer_correctnessok0.3904056185020699533.67
66indication-01localfaithfulnessok0.666666666666666626.284
67indication-01hybridanswer_relevancyok0.86591585036509331.996
68indication-01hybridcontext_recallok0.85.127
69indication-01localanswer_correctnessok0.815478668079759922.987
70indication-01hybridfaithfulnessok1.016.57
71indication-01mixanswer_relevancyok0.83828691901559582.085
72indication-01mixcontext_recallok0.85.266
73indication-01hybridanswer_correctnessok0.710226489822225717.531
74contraindication-01naivefaithfulnessok1.013.677
75contraindication-01naiveanswer_relevancyok0.54875993612267431.943
76contraindication-01naivecontext_recallok0.07.986
77indication-01mixanswer_correctnessok0.446674671757532640.178
78indication-01mixfaithfulnessok0.864864864864864947.779
79contraindication-01localanswer_relevancyok0.01.888
80contraindication-01localcontext_recallok0.07.427
81contraindication-01naiveanswer_correctnessok0.340072030117715223.647
82contraindication-01localfaithfulnessok0.941176470588235320.95
83contraindication-01hybridanswer_relevancyok0.62462345887927872.554
84contraindication-01hybridcontext_recallok0.07.684
85contraindication-01localanswer_correctnessok0.1108526656932738334.453
86contraindication-01hybridfaithfulnessok0.846153846153846134.399
87contraindication-01mixanswer_relevancyok0.01.963
88contraindication-01mixfaithfulnessok0.285714285714285710.903
89contraindication-01mixcontext_recallok0.06.99
90contraindication-01bypassanswer_relevancyok0.30855774888332772.06
91contraindication-01hybridanswer_correctnessok0.348843143652856141.511
92contraindication-01mixanswer_correctnessok0.115258667309313926.242
93interaction-01localanswer_relevancyok0.67049213833098781.667
94interaction-01localfaithfulnessok0.411764705882352917.061
95interaction-01localcontext_recallok0.07.623
96interaction-01hybridfaithfulnessok0.212.766
97interaction-01hybridanswer_relevancyok0.72151574706328651.672
98contraindication-01bypassanswer_correctnessok0.340982582929184848.681
99interaction-01hybridcontext_recallok0.010.94
100interaction-01localanswer_correctnessok0.384239695603664233.411
101interaction-01mixanswer_relevancyok0.87304835264322521.596
102interaction-01mixfaithfulnessok0.666666666666666614.476
103interaction-01mixcontext_recallok0.06.823
104interaction-01bypassanswer_relevancyok0.74130598262512851.913
105interaction-01hybridanswer_correctnessok0.41374411437697436.867
106interaction-01mixanswer_correctnessok0.280282277808828527.753
107interaction-01naiveanswer_relevancyok0.81721165141777491.573
108interaction-01naivefaithfulnessok0.937522.14
109interaction-01naivecontext_recallok0.09.056
110interaction-01bypassanswer_correctnessok0.3715629764141521550.306
111warning-01hybridanswer_relevancyok0.03.699
112warning-01hybridcontext_recallok0.05.158
113warning-01mixanswer_relevancyok0.02.651
114warning-01mixcontext_recallok0.66666666666666666.37
115warning-01bypassanswer_relevancyok0.70477793186082792.714
116warning-01hybridanswer_correctnessok0.081019502474607224.736
117warning-01hybridfaithfulnessok0.588235294117647126.359
118warning-01naiveanswer_relevancyok0.02.696
119warning-01mixfaithfulnessok1.031.472
120warning-01naivecontext_recallok0.05.802
121warning-01naivefaithfulnessok1.014.832
122warning-01localanswer_relevancyok0.02.868
123warning-01naiveanswer_correctnessok0.1064108011386964614.807
124warning-01localcontext_recallok1.04.366
125indication-02bypassanswer_relevancyok0.71103341967664542.434
126warning-01mixanswer_correctnessok0.3513521330858586647.174
127warning-01localfaithfulnessok0.615384615384615422.224
128indication-02naiveanswer_relevancyok0.77906976398222542.969
129indication-02naivecontext_recallok1.08.762
130warning-01localanswer_correctnessok0.1224973836103914724.229
131interaction-01naiveanswer_correctnessok0.555055783434062771.67
132indication-02naivefaithfulnessok1.019.063
133indication-02localanswer_relevancyok0.96889231142584692.668
134indication-02localcontext_recallok0.88888888888888889.624
135indication-02localfaithfulnessok1.019.292
136indication-02hybridanswer_relevancyok0.84590875527854752.298
137indication-02naiveanswer_correctnessok0.87952535129719827.066
138indication-02hybridcontext_recallok1.08.1
139indication-02hybridfaithfulnessok0.916666666666666618.608
140indication-02mixanswer_relevancyok0.80452495825939782.342
141indication-02localanswer_correctnessok0.790691587631273229.27
142indication-02bypassanswer_correctnessok0.88615113165985754.4
143indication-02mixcontext_recallok0.888888888888888810.271
144contraindication-02naiveanswer_relevancyok0.71633121118853552.235
145indication-02hybridanswer_correctnessok0.845944435735495723.328
146contraindication-02naivecontext_recallok0.04.685
147contraindication-02naivefaithfulnessok1.027.572
148indication-02mixfaithfulnessok1.031.836
149contraindication-02localanswer_relevancyok0.67609473642741772.845
150contraindication-02localcontext_recallok0.04.498
151indication-02mixanswer_correctnessok0.584443975444737535.166
152contraindication-02hybridanswer_relevancyok0.02.242
153contraindication-02naiveanswer_correctnessok0.1418478077380278823.373
154contraindication-02hybridcontext_recallok0.04.848
155contraindication-02hybridfaithfulnessok0.818181818181818218.945
156contraindication-02mixanswer_relevancyok0.77708668132181352.263
157contraindication-02localfaithfulnessok0.769230769230769340.044
158contraindication-02mixcontext_recallok1.03.572
159contraindication-02hybridanswer_correctnessok0.1375166201514382620.615
160contraindication-02bypassanswer_relevancyok0.56512201855615442.353
161contraindication-02localanswer_correctnessok0.1870143122769227837.011
162interaction-02localanswer_relevancyok0.332749213548837631.796
163contraindication-02mixfaithfulnessok0.785714285714285729.059
164interaction-02localcontext_recallok0.04.938
165contraindication-02mixanswer_correctnessok0.528316907393887419.373
166interaction-02hybridanswer_relevancyok0.7100106880805641.869
167interaction-02localfaithfulnessok0.2142857142857142720.394
168interaction-02hybridcontext_recallok0.33333333333333336.403
169interaction-02hybridfaithfulnessok0.714285714285714316.228
170warning-01bypassanswer_correctnessok0.1717729831172302241.639
171interaction-02mixanswer_relevancyok0.71554660594008722.491
172interaction-02mixcontext_recallok0.08.913
173interaction-02bypassanswer_relevancyok0.52524033676668992.704
174interaction-02mixfaithfulnessok0.818.739
175interaction-02localanswer_correctnessok0.4305038210309013534.41
176interaction-02hybridanswer_correctnessok0.230534600701503725.879
177interaction-02naiveanswer_relevancyok0.03.255
178interaction-02naivecontext_recallok0.05.051
179contraindication-02bypassanswer_correctnessok0.2896107369257020556.977
180interaction-02naivefaithfulnessok0.87514.994
181warning-02hybridanswer_relevancyok0.02.724
182interaction-02mixanswer_correctnessok0.626907009299484329.494
183warning-02hybridfaithfulnessok0.777777777777777813.601
184warning-02mixanswer_relevancyok0.88739926198468882.146
185warning-02hybridcontext_recallok0.012.75
186interaction-02naiveanswer_correctnessok0.1427984239094770624.042
187warning-02bypassanswer_relevancyok0.66501562694318052.065
188warning-02mixfaithfulnessok1.017.416
189warning-02mixcontext_recallok0.3636363636363636513.192
190warning-02naiveanswer_relevancyok0.83546923388355982.499
191interaction-02bypassanswer_correctnessok0.3689624954667856752.856
192warning-02naivefaithfulnessok1.016.66
193warning-02naivecontext_recallok0.333333333333333313.939
194warning-02localanswer_relevancyok0.5534804617746671.6
195warning-02hybridanswer_correctnessok0.1146089099505867840.771
196warning-02mixanswer_correctnessok0.534692425123384739.149
197warning-02localcontext_recallok0.012.394
198warning-02localfaithfulnessok0.866666666666666721.547
199warning-02naiveanswer_correctnessok0.520870840960799230.929
200warning-02localanswer_correctnessok0.1088221757133295334.551
201warning-02bypassanswer_correctnessok0.4247047838050592761.649