MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration

arXiv:2606.22826 · cs.AI · Submitted 2026-06-22 · Read on arXiv

cs.AI

Submitted: 2026-06-22

Updated: 2026-09-30

Code: https://github.com/amd/quark

Terminology

• Calibration — 5× in this paper · explained in 7 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Monte Carlo Informed N-sizing for Compact Evaluation — 1× in this paper

Sources

• Phi-4 Technical Report
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• Mistral 7B
• MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
• Qwen3 Technical Report
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems