List your company

Question Answering on HotpotQA (F1, Avg Cost)

41.02F1 ScoreRelevance
13.553620.684327.81534.9457Jun 1, 2026

Evaluation results

MethodLinks
RelevanceBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0641.0215.5
MMRBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0638.9710.88
GreedyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0637.818
RelevanceBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0637.7318.1
RelevanceBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0637.1419.2
KnapsackBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.063719.24
RelevanceBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0636.9912.9
KnapsackBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0636.6517.1
KnapsackBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0636.6212.65
GreedyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0636.2612.56
GreedyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0636.1915.08
GreedyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0635.7419.24
MMRBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0635.6910.88
MMRBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0635.199.82
GreedyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0635.1716.98
MMRBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0634.6810.88
MMRBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.528.04
RelevanceBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.479.2
KnapsackBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0634.4318.06
GreedyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.218.93
Top-kBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0633.99—
KnapsackBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0633.910
KnapsackBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0633.5915.38
KnapsackBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0633.564.77
RelevanceBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0633.5517.2
MMRBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0633.5110.61
RelevanceBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0633.450
RedundancyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0633.320.19
KnapsackBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0633.059.17
Top-kBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0632.98—
Top-kBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0632.69—
RedundancyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0632.290.19
GreedyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0631.354.74
RelevanceBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0631.234.8
RedundancyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0630.710.19
RedundancyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0630.620
GreedyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0630.480
RedundancyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0630.460.19
RedundancyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0630.360.15
Top-kBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0630.24—
MMRBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0629.690
MMRBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0628.784.67
RedundancyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0628.740.19
RedundancyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0628.530.19
Top-kBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0626.53—
Top-kBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0615.36—
Vanilla LLMBackbone=Llama3.1-8B-instruct2026.0614.61—