List your company
ResearchFormerly WizWand

Veracity prediction on Ru22fact (test)

90MF1SEEK
59.8467.6775.583.33May 21, 2025Jul 21, 2025Sep 21, 2025Nov 22, 2025Jan 22, 2026Mar 25, 2026May 26, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SEEKModel=Gemma2026.0590
SEEKModel=Mistral2026.0590
SEEKModel=LLaMA2026.0589
Semantic ChunkingModel=LLaMA2026.0579
Semantic ChunkingModel=Mistral2026.0579
Semantic ChunkingModel=Gemma2026.0578
MistralMistralEvaluation Protocol=QLoRA2025.0573
LLMModel=LLaMA2026.0573
GemmaGemmaEvaluation Protocol=QLoRA2025.0572
LLMModel=Mistral2026.0572
Sentence ChunkingModel=Mistral2026.0572
LlamaLlamaEvaluation Protocol=QLoRA2025.0571
Sentence ChunkingModel=LLaMA2026.0571
Sentence ChunkingModel=Gemma2026.0571
QwenQwenEvaluation Protocol=QLoRA2025.0570
LLMModel=Gemma2026.0570
XLMRQwenEvaluation Protocol=Fine-Tuning2025.0568
mBERTMistralEvaluation Protocol=Fine-Tuning2025.0568
XLMRMistralEvaluation Protocol=Fine-Tuning2025.0567
mBERTLlamaEvaluation Protocol=Fine-Tuning2025.0567
mBERTQwenEvaluation Protocol=Fine-Tuning2025.0566
XLMRGemmaEvaluation Protocol=Fine-Tuning2025.0565
XLMRLlamaEvaluation Protocol=Fine-Tuning2025.0565
mBERTGemmaEvaluation Protocol=Fine-Tuning2025.0565
Zeng et al. (2024)Evaluation Protocol=Baseline2025.0561