List your company

Hallucination Detection on FinQA retrieval-equalized (test)

2.1P95 Latency (s)HHEM
1.6884.4697.2510.031Apr 26, 2026

Evaluation results

MethodLinks
HHEM2026.042.10.00176.3
FINGROUNDModel Size=8B, Hardware=A1002026.043.80.00391.4
FINGROUNDModel Size=8B, Hardware=A10G2026.045.90.00291.4
GPT-4oModel Role=teacher2026.048.20.04795
SelfCheckGPT2026.0412.40.06272.8