Correctness Prediction on Notable People
82.5AUROCDirection
Evaluation Results
| Method | Links | |
|---|---|---|
| DirectionModel=DeepSeek R1 Distill Qwen 32B, Train dataset=TriviaQA2025.09 | 82.5 | |
| DirectionModel=Qwen 2.5 7B Instruct, Train dataset=TriviaQA2025.09 | 80 | |
| DirectionModel=Mistral 7B Instruct v0.3, Train dataset=TriviaQA2025.09 | 76 | |
| AssessorModel=Qwen 2.5 7B Instruct, Assessor type=logistic regression2025.09 | 72.3 | |
| DirectionModel=Llama 3.1 8B, Train dataset=TriviaQA2025.09 | 72.2 | |
| AssessorModel=DeepSeek R1 Distill Qwen 32B, Assessor type=logistic regression2025.09 | 70.9 | |
| DirectionModel=Llama 3.3 70B Instruct, Train dataset=TriviaQA2025.09 | 70.8 | |
| DirectionModel=Ministral 8B Instruct 2410, Train dataset=TriviaQA2025.09 | 68 | |
| AssessorModel=Mistral 7B Instruct v0.3, Assessor type=logistic regression2025.09 | 67.3 | |
| Verb. conf.Model=Qwen 2.5 7B Instruct2025.09 | 63.7 | |
| AssessorModel=Llama 3.1 8B, Assessor type=logistic regression2025.09 | 63 | |
| Verb. conf.Model=Mistral 7B Instruct v0.32025.09 | 62.5 | |
| AssessorModel=Ministral 8B Instruct 2410, Assessor type=logistic regression2025.09 | 62.3 | |
| Verb. conf.Model=DeepSeek R1 Distill Qwen 32B2025.09 | 60.5 | |
| Verb. conf.Model=Llama 3.3 70B Instruct2025.09 | 59.4 | |
| AssessorModel=Llama 3.3 70B Instruct, Assessor type=logistic regression2025.09 | 58.3 | |
| Verb. conf.Model=Ministral 8B Instruct 24102025.09 | 50 | |
| Verb. conf.Model=Llama 3.1 8B2025.09 | 49.9 |