Text Classification on Forbidden Question Set
89.85AccuracyCalibration w/ ADAMAB
Evaluation Results
| Method | Links | |
|---|---|---|
| Calibration w/ ADAMABProtocol=Few-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 89.85 | |
| Calibration w/ ADAMABProtocol=Zero-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 89.54 | |
| Calibration w/ ADAMABProtocol=Zero-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 88.92 | |
| Calibration w/ ADAMABProtocol=Few-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 88.92 | |
| Calibration w/ random aug.Protocol=Few-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 87.38 | |
| Calibration w/ random aug.Protocol=Zero-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 86.15 | |
| Calibration w/ random aug.Protocol=Zero-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 86.15 | |
| Calibration w/ random aug.Protocol=Few-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 84.62 | |
| BGE-reranker-v2-m3Protocol=Few-shot, # Params=0.568B2026.02 | 83.39 | |
| Calibration w/ only init setProtocol=Zero-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 82.15 | |
| Gemini2.0-Flash-LiteProtocol=Few-shot, # Params=n/a2026.02 | 81.85 | |
| Calibration w/ only init setProtocol=Few-shot, Backbone=OpenAI-text-embedding-3-small, # Params=+2.654M2026.02 | 81.23 | |
| OpenAI-text-embedding-3-smallProtocol=Few-shot, # Params=n/a2026.02 | 80.62 | |
| GPT-4o-miniProtocol=Zero-shot, # Params=n/a2026.02 | 80.31 | |
| Calibration w/ only init setProtocol=Few-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 80.31 | |
| Llama-3.2Protocol=Few-shot, # Params=90B2026.02 | 79.69 | |
| Mistral-SmallProtocol=Few-shot, # Params=24B2026.02 | 79.39 | |
| Cohere-v3.5Protocol=Few-shot, # Params=n/a2026.02 | 78.77 | |
| Calibration w/ only init setProtocol=Zero-shot, Backbone=QWen-3-emb-06b, # Params=+1.180M2026.02 | 78.46 | |
| Mistral-SmallProtocol=Zero-shot, # Params=24B2026.02 | 77.23 | |
| GPT-4o-miniProtocol=Few-shot, # Params=n/a2026.02 | 76 | |
| Llama-3.2Protocol=Zero-shot, # Params=90B2026.02 | 75.08 | |
| Gemini2.0-Flash-LiteProtocol=Zero-shot, # Params=n/a2026.02 | 74.77 | |
| OpenAI-text-embedding-3-smallProtocol=Zero-shot, # Params=n/a2026.02 | 72.92 | |
| QWen-3-emb-06bProtocol=Few-shot, # Params=0.596B2026.02 | 71.69 | |
| QWen-3-emb-06bProtocol=Zero-shot, # Params=0.596B2026.02 | 60.31 | |
| Cohere-v3.5Protocol=Zero-shot, # Params=n/a2026.02 | 54.15 | |
| BGE-reranker-v2-m3Protocol=Zero-shot, # Params=0.568B2026.02 | 46.15 |