List your company

Question Answering on TriviaQA (F1, avg_cost)

64.47F1 ScoreRelevance
22.672433.523744.37555.2263Jun 1, 2026

Evaluation results

MethodLinks
RelevanceBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0664.4718
KnapsackBgt/k=15, Backbone=Llama3.1-8B-instruct2026.066412.3
MMRBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0663.789.87
GreedyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0663.7119.38
MMRBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0663.5511.18
Top-kBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0663.23—
MMRBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0662.898
KnapsackBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0662.5722.3
KnapsackBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0662.2919.59
GreedyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0662.1214.94
MMRBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0661.9210.86
MMRBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0661.8311.18
RelevanceBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0661.8122.3
GreedyBackbone=Qwen3-8B, Bgt/k=302026.0661.7919.4
KnapsackBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0661.6917.81
GreedyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0661.4412.03
RelevanceBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0661.190
GreedyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0661.1817.6
MMRBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0661.0711.16
RelevanceBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0660.9312.6
RelevanceBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0660.874.9
RelevanceBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0660.6219.7
Top-kBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0660.4—
MMRBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0660.374.73
GreedyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0660.3422.3
RelevanceBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0660.2915.6
KnapsackBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0660.0515.45
Top-kBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0659.45—
GreedyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0659.368.78
RelevanceBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0659.189.1
Top-kBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0659.13—
RedundancyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0659.050.09
KnapsackBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0658.874.82
RedundancyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0658.660
KnapsackBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0658.58.87
RedundancyBackbone=Qwen3-8B, Bgt/k=202026.0658.460.1
RedundancyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0658.240.09
GreedyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0658.030
RedundancyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0657.660.09
RedundancyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0657.60.09
RedundancyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0657.420.09
RedundancyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0657.410.09
MMRBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0656.990
GreedyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0656.844.82
RedundancyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0656.260.09
KnapsackBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0656.130
Top-kBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0654.38—
Top-kBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0647.41—
Vanilla LLMBackbone=Qwen3-8B, Bgt/k=-2026.0643.57—
Vanilla LLMBackbone=Llama3.1-8B-instruct2026.0624.28—