Group Assignment on RadTimeline (test)
86CoNLL F1Llama-3.1 Prompting
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.1 PromptingGroup names source=Oracle, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 86 | |
| GPT-4o PromptingGroup names source=Oracle, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 85 | |
| GPT-4o PromptingGroup names source=GPT-4o, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 84 | |
| Llama-3.1 PromptingGroup names source=Oracle, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 84 | |
| GPT-4o PromptingGroup names source=Oracle, Prompting strategy=Single, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 84 | |
| GPT-4o PromptingGroup names source=Oracle, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 83 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=Oracle, Instruction type=Task-specific, Model selection=e5-mistral-7b-instruct2026.03 | 83 | |
| GPT-4o PromptingGroup names source=GPT-4o, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 82 | |
| GPT-4o PromptingGroup names source=GPT-4o, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 82 | |
| Llama-3.1 PromptingGroup names source=GPT-4o, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 81 | |
| GPT-4o PromptingGroup names source=GPT-4o, Prompting strategy=Single, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 80 | |
| GPT-4o PromptingGroup names source=Oracle, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 80 | |
| Llama-3.1 PromptingGroup names source=GPT-4o, Prompting strategy=Single, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 79 | |
| Llama-3.1 PromptingGroup names source=Llama-3.1, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 78 | |
| GPT-4o PromptingGroup names source=Llama-3.1, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 78 | |
| Llama-3.1 PromptingGroup names source=Oracle, Prompting strategy=Single, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 78 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=Oracle, Instruction type=General, Model selection=e5-mistral-7b-instruct2026.03 | 78 | |
| Llama-3.1 PromptingGroup names source=Llama-3.1, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 77 | |
| GPT-4o PromptingGroup names source=Llama-3.1, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 77 | |
| GPT-4o PromptingGroup names source=Llama-3.1, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 77 | |
| Llama-3.1 PromptingGroup names source=GPT-4o, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 77 | |
| Llama-3.1 PromptingGroup names source=GPT-4o, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 75 | |
| Llama-3.1 PromptingGroup names source=Llama-3.1, Prompting strategy=Single, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 74 | |
| GPT-4o PromptingGroup names source=Llama-3.1, Prompting strategy=Single, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 73 | |
| Llama-3.1 PromptingGroup names source=Oracle, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 73 | |
| Llama-3.1 PromptingGroup names source=No groups, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 72 | |
| GPT-4o PromptingGroup names source=No groups, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=GPT-4o2026.03 | 72 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=Llama-3.1, Instruction type=Task-specific, Model selection=e5-mistral-7b-instruct2026.03 | 70 | |
| GPT-4o PromptingGroup names source=No groups, Prompting strategy=Multiple, Learning setting=Zero-shot, Model selection=GPT-4o2026.03 | 70 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=GPT-4o, Instruction type=Task-specific, Model selection=e5-mistral-7b-instruct2026.03 | 69 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=Llama-3.1, Instruction type=General, Model selection=e5-mistral-7b-instruct2026.03 | 68 | |
| Llama-3.1 PromptingGroup names source=No groups, Prompting strategy=Multiple, Learning setting=Few-shot, Model selection=Llama-3.12026.03 | 68 | |
| Llama-3.1 PromptingGroup names source=Llama-3.1, Prompting strategy=Single, Learning setting=Zero-shot, Model selection=Llama-3.12026.03 | 66 | |
| e5-mistral-7b-instruct EmbeddingGroup names source=GPT-4o, Instruction type=General, Model selection=e5-mistral-7b-instruct2026.03 | 65 |