List your company
ResearchFormerly WizWand

Hate speech classification on Implicit Hate (test)

0.67Macro F1Llama_Full
0.12920.26960.410.5504Sep 18, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Llama_FullTraining Paradigm=Full, Model Backbone=Llama, Data%=100%2025.090.67100
T5_FullTraining Paradigm=Full, Model Backbone=T5, Data%=100%2025.090.6496
ModernBERTTraining Paradigm=Full, Model Backbone=ModernBERT, Data%=100%2025.090.6496
SMARTER (Llama_DPO-256)Training Paradigm=DPO, K shots=256, Model Backbone=Llama, Data%=57%2025.090.690
SMARTER (T5_DPO-256)Training Paradigm=DPO, K shots=256, Model Backbone=T5, Data%=57%2025.090.5988
GPT-5-chatTraining Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-5-chat2025.090.5887
GPT-4.1Training Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-4.12025.090.5785
Qwen-32BTraining Paradigm=Zero-shot, K shots=0, Model Backbone=Qwen-32B2025.090.4973
Qwen-32BTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=Qwen-32B2025.090.4872
GPT-4o-miniTraining Paradigm=Zero-shot, K shots=0, Model Backbone=GPT-4o-mini2025.090.4263
GPT-5-chatTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-5-chat2025.090.460
GPT-4.1Training Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-4.12025.090.3857
GPT-4o-miniTraining Paradigm=16-shot ICL, K shots=16, Model Backbone=GPT-4o-mini2025.090.1522