List your company

Hallucination Detection on HalluScore

97.77F1-ScoreCrossHallu
27.46645.71863.9782.222Jul 4, 2026

Evaluation results

MethodLinks
CrossHalluBackbone=Phi4-mini, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.0797.7757.1997.04
CrossHalluBackbone=Phi4-mini, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0797.7772.5998.43
CrossHalluBackbone=Aya, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.079780.3797.96
CrossHalluBackbone=Aya, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0796.6986.998.66
CrossHalluBackbone=Mistral, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.0796.1869.2895.56
CrossHalluBackbone=Silma, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.0795.9661.8494.8
CrossHalluBackbone=Aya, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0794.7976.9898.07
CrossHalluBackbone=Silma, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0791.9464.895.64
CrossHalluBackbone=Silma, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0790.9662.5794.66
CrossHalluBackbone=Allam, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0788.9555.2184.22
CrossHalluBackbone=Allam, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.0787.8960.486.41
CrossHalluBackbone=Mistral, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0786.4671.895.1
CrossHalluBackbone=Allam, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0786.2956.3983.54
CrossHalluBackbone=Phi4-mini, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0784.8363.7997.93
CrossHalluBackbone=Qwen2.5, Train dataset=HalluScore, Transfer setting group=Same-language baseline (BS)2026.0784.5772.4487.17
CrossHalluBackbone=Mistral, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0777.7466.1795.39
CrossHalluBackbone=Qwen2.5, Train dataset=TruthfulQA EN, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0772.1869.0385.27
CrossHalluBackbone=Qwen2.5, Train dataset=TruthfulQA AR, Transfer setting group=Cross-domain (CD)2026.0730.1768.9485.24