List your company

Hallucination Detection on TruthfulQA EN

88.34F1-ScoreCrossHallu
2.831225.030647.2369.4294Jul 4, 2026

Evaluation results

MethodLinks
CrossHalluBackbone=Aya, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0788.3482.8288.85
CrossHalluBackbone=Allam, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0784.7771.383.47
CrossHalluBackbone=Allam, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.0783.3858.1976.52
CrossHalluBackbone=Mistral, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0782.6762.6779.64
CrossHalluBackbone=Allam, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0781.8861.4478.05
CrossHalluBackbone=Aya, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0779.3862.3473.45
CrossHalluBackbone=Phi4-mini, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.077966.8480.02
CrossHalluBackbone=Aya, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.077959.3976.9
CrossHalluBackbone=Phi4-mini, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.077962.8477.99
CrossHalluBackbone=Phi4-mini, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0778.8170.6484.3
CrossHalluBackbone=Mistral, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0778.8170.6484.3
CrossHalluBackbone=Silma, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0777.0759.1673.08
CrossHalluBackbone=Silma, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.0776.7749.7760.64
CrossHalluBackbone=Silma, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0776.4570.0175.51
CrossHalluBackbone=Mistral, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.0776.1966.3381
CrossHalluBackbone=Qwen2.5, Train dataset=HalluScore, Transfer setting group=Cross-lingual + cross-domain (CL-CD)2026.0759.2258.3455.1
CrossHalluBackbone=Qwen2.5, Train dataset=TruthfulQA EN, Transfer setting group=Same-language baseline (BS)2026.0757.8669.7566.88
CrossHalluBackbone=Qwen2.5, Train dataset=TruthfulQA AR, Transfer setting group=Cross-lingual (CL)2026.076.1261.5655.75