List your company
ResearchFormerly WizWand

Hate speech classification on Latent Hate (test)

69Macro F1 ScoreSMARTER (Llama_DPO-256)
23.2435.124758.88Sep 18, 2025
Updated 6mo ago

Evaluation results

MethodLinks
SMARTER (Llama_DPO-256)Training Paradigm=DPO, K shots=256, Model Backbone=Llama, Data%=7%2025.0969100
SMARTER (T5_DPO-256)Training Paradigm=DPO, K shots=256, Model Backbone=T5, Data%=7%2025.096594
GPT-4.1Training Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-4.12025.096391
Llama_FullTraining Paradigm=Full, Model Backbone=Llama, Data%=100%2025.096290
T5_FullTraining Paradigm=Full, Model Backbone=T5, Data%=100%2025.096188
ModernBERTTraining Paradigm=Full, Model Backbone=ModernBERT, Data%=100%2025.096188
GPT-4.1Training Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-4.12025.096087
GPT-5-chatTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-5-chat2025.096087
Qwen-32BTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=Qwen-32B2025.095783
GPT-4o-miniTraining Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-4o-mini2025.095478
GPT-5-chatTraining Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-5-chat2025.095174
Qwen-32BTraining Paradigm=Zero-shot, K shots=0, Model Backbone=Qwen-32B2025.094768
GPT-4o-miniTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-4o-mini2025.092536