List your company

Correctness Prediction on Notable People

82.5AUROCDirection
48.59657.39866.275.002Sep 12, 2025

Evaluation results

MethodLinks
DirectionModel=DeepSeek R1 Distill Qwen 32B, Train dataset=TriviaQA2025.0982.5
DirectionModel=Qwen 2.5 7B Instruct, Train dataset=TriviaQA2025.0980
DirectionModel=Mistral 7B Instruct v0.3, Train dataset=TriviaQA2025.0976
AssessorModel=Qwen 2.5 7B Instruct, Assessor type=logistic regression2025.0972.3
DirectionModel=Llama 3.1 8B, Train dataset=TriviaQA2025.0972.2
AssessorModel=DeepSeek R1 Distill Qwen 32B, Assessor type=logistic regression2025.0970.9
DirectionModel=Llama 3.3 70B Instruct, Train dataset=TriviaQA2025.0970.8
DirectionModel=Ministral 8B Instruct 2410, Train dataset=TriviaQA2025.0968
AssessorModel=Mistral 7B Instruct v0.3, Assessor type=logistic regression2025.0967.3
Verb. conf.Model=Qwen 2.5 7B Instruct2025.0963.7
AssessorModel=Llama 3.1 8B, Assessor type=logistic regression2025.0963
Verb. conf.Model=Mistral 7B Instruct v0.32025.0962.5
AssessorModel=Ministral 8B Instruct 2410, Assessor type=logistic regression2025.0962.3
Verb. conf.Model=DeepSeek R1 Distill Qwen 32B2025.0960.5
Verb. conf.Model=Llama 3.3 70B Instruct2025.0959.4
AssessorModel=Llama 3.3 70B Instruct, Assessor type=logistic regression2025.0958.3
Verb. conf.Model=Ministral 8B Instruct 24102025.0950
Verb. conf.Model=Llama 3.1 8B2025.0949.9