List your company

Question Answering on NQ (avg_cost, F1)

44.11F1 ScoreMMR
11.256419.785728.31536.8443Jun 1, 2026

Evaluation results

MethodLinks
MMRBackbone=Qwen3-8B, Bgt/k=102026.0644.118.8
RelevanceBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0642.4413.6
RelevanceBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0641.3616.8
RedundancyBackbone=Qwen3-8B, Bgt/k=∞2026.0640.850.3
Top-kBackbone=Qwen3-8B, Bgt/k=152026.0640.1—
Top-kBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0639.6—
Top-kBackbone=Qwen3-8B, Bgt/k=252026.0639.6—
RelevanceBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0639.5120.9
RelevanceBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0639.480
Top-kBackbone=Qwen3-8B, Bgt/k=202026.0639.06—
MMRBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0638.3312.56
Top-kBackbone=Qwen3-8B, Bgt/k=302026.0638.25—
KnapsackBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0637.6520.72
Top-kBackbone=Qwen3-8B, Bgt/k=52026.0637.14—
RelevanceBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0637.129.7
KnapsackBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0636.8816.49
GreedyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0636.8716.1
Top-kBackbone=Qwen3-8B, Bgt/k=102026.0636.87—
GreedyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0636.6620.54
Top-kBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0636.57—
MMRBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0636.5512.56
MMRBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0636.4512.04
GreedyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0636.3412.94
RedundancyBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0636.230.3
RedundancyBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0636.230.3
KnapsackBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0635.914.97
RedundancyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0635.730.3
KnapsackBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0635.713.21
GreedyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0635.420
KnapsackBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0635.3123.46
RedundancyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0635.010.3
RedundancyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0634.870.3
RelevanceBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0634.7123.5
MMRBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0634.711.12
RedundancyBgt/k=15, Backbone=Llama3.1-8B-instruct2026.0634.70.3
Top-kBgt/k=20, Backbone=Llama3.1-8B-instruct2026.0634.52—
KnapsackBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.529.46
GreedyBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.439.4
GreedyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0634.254.89
MMRBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0634.218.78
GreedyBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0634.1718.72
RedundancyBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0634.120.26
RelevanceBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0633.95
GreedyBgt/k=∞, Backbone=Llama3.1-8B-instruct2026.0633.623.46
Top-kBgt/k=10, Backbone=Llama3.1-8B-instruct2026.0633.55—
MMRBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0633.520
KnapsackBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0633.3518.94
Top-kBgt/k=30, Backbone=Llama3.1-8B-instruct2026.0633.33—
MMRBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0633.3112.46
MMRBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0633.254.86
KnapsackBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0632.210
RedundancyBgt/k=0, Backbone=Llama3.1-8B-instruct2026.0632.140
RelevanceBgt/k=25, Backbone=Llama3.1-8B-instruct2026.0631.9319.2
Top-kBgt/k=5, Backbone=Llama3.1-8B-instruct2026.0627.55—
Vanilla LLMBackbone=Qwen3-8B, Bgt/k=-2026.0619.81—
Vanilla LLMBackbone=Llama3.1-8B-instruct2026.0612.52—