Pairwise Value Extraction on ARXIV2TABLE
49Precisioniterative batch-based generation method
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| iterative batch-based generation methodBackbone Model=GPT-o32025.04 | 49 | 59 | 53.5 | |
| iterative batch-based generation methodBackbone Model=GPT-4o, Chain of Thought=true2025.04 | 47 | 57 | 51.5 | |
| iterative batch-based generation methodBackbone Model=GPT-4o2025.04 | 45.9 | 55.7 | 50.3 | |
| iterative batch-based generation methodBackbone Model=GPT-4o-mini2025.04 | 43.5 | 51.9 | 47.3 | |
| iterative batch-based generation methodBackbone Model=Mistral-Large (123B)2025.04 | 42 | 49.2 | 45.3 | |
| iterative batch-based generation methodBackbone Model=DeepSeek-V3 (685B)2025.04 | 40.4 | 49.8 | 44.6 | |
| Newman et al.Backbone Model=GPT-4o, Chain of Thought=true2025.04 | 39 | 42 | 40.5 | |
| Newman et al.Backbone Model=GPT-4o2025.04 | 36.9 | 40 | 38.4 | |
| iterative batch-based generation methodBackbone Model=LLaMa-3.3 (70B)2025.04 | 36.4 | 46.9 | 41 | |
| Newman et al.Backbone Model=GPT-4o-mini2025.04 | 35 | 37.8 | 36.3 | |
| Newman et al.Backbone Model=DeepSeek-V3 (685B)2025.04 | 33.3 | 36.5 | 34.8 | |
| Newman et al.Backbone Model=Mistral-Large (123B)2025.04 | 29.9 | 35.1 | 32.3 | |
| Newman et al.Backbone Model=LLaMa-3.3 (70B)2025.04 | 29.5 | 30.2 | 29.8 | |
| Baseline 1Backbone Model=GPT-4o2025.04 | 29 | 34.7 | 31.6 | |
| Baseline 1Backbone Model=DeepSeek-V3 (685B)2025.04 | 28.7 | 31.8 | 30.1 | |
| Baseline 1Backbone Model=LLaMa-3.3 (70B)2025.04 | 28.4 | 31.8 | 30 | |
| Baseline 2Backbone Model=DeepSeek-V3 (685B)2025.04 | 25.7 | 32.7 | 28.8 | |
| Baseline 1Backbone Model=GPT-4o-mini2025.04 | 25 | 31 | 27.7 | |
| Baseline 2Backbone Model=GPT-4o-mini2025.04 | 21.6 | 28.3 | 24.5 | |
| Baseline 2Backbone Model=GPT-4o2025.04 | 19.4 | 33.6 | 24.6 | |
| Baseline 2Backbone Model=Mistral-Large (123B)2025.04 | 17.8 | 30.7 | 22.6 | |
| Baseline 1Backbone Model=Mistral-Large (123B)2025.04 | 15.5 | 24.7 | 19 | |
| Baseline 2Backbone Model=LLaMa-3.3 (70B)2025.04 | 11.2 | 22.5 | 15 |