Research paper

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

Published by Association for Computational LinguisticsOct 2026PDF

See how calibration can help reduce the number of test cases needed for model evaluation.

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

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Devleena Das, Rajeev Patwari, Vikram Kumar Bukka, Nithin Kumar Guggilla, Elliott Delaye, Ashish Sirasao. MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track. © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/2026.emnlp-industry.84. Original PDF, unmodified.

CC BY 4.0

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

Related research.

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?

Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot