List your company

Risk Decision-making on DeXposure-Bench frozen 2025 (test)

0.72Precisionpersist. rules
0.5640.60450.6450.6855Jun 17, 2026

Evaluation results

MethodLinks
persist. rulesPred.=persist., Decision=rules2026.060.720.0040.0076———0.514
DeXposure-FM rulesPred.=DeXposure-FM, Decision=rules2026.060.60.010.019———0.257
DeXposure-FM LLM + safety gatePred.=DeXposure-FM, Decision=LLM + safety gate2026.060.580.0120.02342.450.43710.435
LLM (no FM)Decision=LLM (no FM)2026.060.5750.0090.01842.24—10.532
DeXposure-FM LLMPred.=DeXposure-FM, Decision=LLM2026.060.570.0120.02412.410.44810.488