List your company
ResearchFormerly WizWand

Aggregate NLP Tasks on Average (Emotion, Irony, Stance, MRPC, RTE)

2.93Delta 1Qwen2.5-14B
1.80089.422917.04524.6671Nov 24, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Qwen2.5-14Bscenario=updated dataset (ours)2025.112.930.7
Llama3-8Bscenario=updated dataset (ours)2025.114.381.29
Yi1.5-9Bscenario=updated dataset (ours)2025.115.740.59
Qwen2.5-7Bscenario=updated dataset (ours)2025.115.831.19
Qwen2.5-14Bscenario=semantic dataset2025.116.061.72
Ministral-8Bscenario=updated dataset (ours)2025.117.160.39
Mistral-12Bscenario=updated dataset (ours)2025.117.191.59
Qwen2.5-7Bscenario=semantic dataset2025.117.661.95
Yi1.5-6Bscenario=updated dataset (ours)2025.118.881.19
Llama3-8Bscenario=semantic dataset2025.1110.622.09
Yi1.5-9Bscenario=semantic dataset2025.1110.712.33
Qwen2.5-7Bscenario=original dataset2025.1112.014.74
Mistral-12Bscenario=semantic dataset2025.1112.612.36
Ministral-8Bscenario=semantic dataset2025.1112.841.81
Yi1.5-6Bscenario=semantic dataset2025.1113.61.49
Llama2-13Bscenario=updated dataset (ours)2025.1116.271.01
Qwen2.5-14Bscenario=original dataset2025.1117.457.19
Llama3-8Bscenario=original dataset2025.1118.956.84
Llama2-13Bscenario=semantic dataset2025.1120.922.38
Yi1.5-6Bscenario=original dataset2025.1123.517.69
Ministral-8Bscenario=original dataset2025.1125.177.7
Yi1.5-9Bscenario=original dataset2025.1125.2210.65
Mistral-12Bscenario=original dataset2025.1126.58.86
Llama2-13Bscenario=original dataset2025.1131.167.07