Citation Prediction on NFCorpus (test)
98.8AccuracyEP_CRIT
Evaluation Results
| Method | Links | |
|---|---|---|
| EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 98.8 | |
| EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 98.8 | |
| EP_CRITModel=gpt-5-2025-08-072025.10 | 97.6 | |
| EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 97.6 | |
| EP_CRITModel=gpt-5-2025-08-072025.10 | 97.6 | |
| EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 97.6 | |
| EP+SEM_CRITModel=gpt-5-2025-08-072025.10 | 96.8 | |
| EP+SEM_CRITModel=gpt-5-2025-08-072025.10 | 96.8 | |
| EP_LABELModel=gpt-5-2025-08-072025.10 | 96.4 | |
| EP_LABELModel=gpt-5-2025-08-072025.10 | 96.4 | |
| EP+SEM_CRITModel=gpt-oss-20b2025.10 | 95.6 | |
| EP+SEM_CRITModel=gpt-oss-20b2025.10 | 95.6 | |
| EP_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 95.2 | |
| EP+SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 95.2 | |
| EP_CRITModel=gpt-oss-20b2025.10 | 94.8 | |
| EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.10 | 94.8 | |
| EP_LABELModel=qwen3-235b-a22b-instruct-25072025.10 | 94.8 | |
| EP_CRITModel=gpt-oss-20b2025.10 | 94.8 | |
| EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.10 | 94.8 | |
| EP_CRITModel=llama-4-scout2025.10 | 93.6 | |
| SEM_CRITModel=gpt-5-2025-08-072025.10 | 91.6 | |
| SEM_CRITModel=gpt-5-2025-08-072025.10 | 91.6 | |
| EP+SEM_CRITModel=llama-4-scout2025.10 | 91.2 | |
| zero_shotModel=gpt-oss-20b2025.10 | 90.4 | |
| EP_LABELModel=llama-4-scout2025.10 | 90.4 | |
| zero_shotModel=gpt-oss-20b2025.10 | 90.4 | |
| zero_shotModel=gpt-5-2025-08-072025.10 | 90 | |
| EP+SEM_CRITModel=gpt-4o-mini-2024-07-182025.10 | 90 | |
| zero_shotModel=gpt-5-2025-08-072025.10 | 90 | |
| SEM_CRITModel=gpt-oss-20b2025.10 | 89.6 | |
| SEM_CRITModel=gpt-oss-20b2025.10 | 89.6 | |
| EP_CRITModel=gpt-4o-mini-2024-07-182025.10 | 89.2 | |
| SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 88.4 | |
| SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 88.4 | |
| EP_LABELModel=gpt-oss-20b2025.10 | 88 | |
| EP_LABELModel=gpt-oss-20b2025.10 | 88 | |
| zero_shotModel=qwen3-vl-235b-a22b-thinking2025.10 | 87.6 | |
| zero_shotModel=qwen3-vl-235b-a22b-thinking2025.10 | 87.6 | |
| zero_shotModel=gpt-4o-mini-2024-07-182025.10 | 87.2 | |
| zero_shotModel=qwen3-235b-a22b-instruct-25072025.10 | 86.4 | |
| zero_shotModel=llama-4-scout2025.10 | 85.6 | |
| SEM_CRITModel=gpt-4o-mini-2024-07-182025.10 | 85.2 | |
| SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 85.2 | |
| EP_LABELModel=gpt-4o-mini-2024-07-182025.10 | 83.6 | |
| SEM_CRITModel=llama-4-scout2025.10 | 83.6 |