List your company

Hallucination Detection on Custom Dataset

72.9F1 ScoreEnsemble+ML
-2.91616.76736.4556.133Mar 17, 2026

Evaluation results

MethodLinks
Ensemble+ML2026.0372.973.574.872.4
Binary Logits2026.0372.775.881.566.3
Features+ML2026.0371.775.176.767.3
Rule-Based (OR)2026.0371.7———
Rule-Based (AND)2026.0368.9———
Non-LLM Baseline2026.0366.167.269.164.4
Adversarial2026.0352———
DSPy MIPRO2026.0345.377.58033.3
DSPy Baseline2026.034075.68028.3
RefChecker2026.0327.145.122.735.4
SelfCheckGPT2026.0326.552.357.617.2
GPT-4o-mini2026.0316.954.61009.3
GPT-52026.0315.893.614.615.4
O32026.038.994.310.77.6
SAC3Backbone=L3.3-70B2026.0309000