SOURCE-LINKED INTELLIGENCE

Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Group-based reinforcement learning with verifiable rewards (RLVR) scoresmultiple completions per prompt using automatic verifiers. Analysesbased on independent verifier errors may overlook dependence associatedwith shared answer formats. We investigate this dependence in24,998 groups of eight completions generated by Qwen2.5-1.5B onMATH, GSM8K, and DeepMath-103K. We estimate a pooled within-groupverifier-error correlation of 0.530 (95% confidence interval:0.500--0.560). Under an exchangeable-error model, this correspondsto a design-effect-adjusted effective sample size of 1.70 for aneight-comp

Read original source ↗ Open in workspace

recordType

paper

region

Global