LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
This addresses the need for automated benchmark generation to improve efficiency and reliability in evaluating LLMs, though it is incremental as it builds on existing LLM-based methods.
The paper tackles the problem of generating reliable, generic, and efficient benchmarks for matching large language models (LLMs) with applications by proposing BenchMaker, which achieves performance comparable to human-annotated benchmarks and delivers highly consistent evaluation results across 12 LLMs with a Pearson correlation of 0.967 against MMLU-Pro, costing only $0.005 and 0.38 minutes per sample.
The rapid advancement of large language models (LLMs) has led to a surge in both model supply and application demands. To facilitate effective matching between them, reliable, generic and efficient benchmark generators are widely needed. However, human annotators are constrained by inefficiency, and current LLM benchmark generators not only lack generalizability but also struggle with limited reliability, as they lack a comprehensive evaluation framework for validation and optimization. To fill this gap, we first propose an automated and unbiased evaluation framework, structured around four dimensions and ten criteria. Under this framework, we carefully analyze the advantages and weaknesses of directly prompting LLMs as generic benchmark generators. To enhance the reliability, we introduce a series of methods to address the identified weaknesses and integrate them as BenchMaker. Experiments across multiple LLMs and tasks confirm that BenchMaker achieves superior or comparable performance to human-annotated benchmarks on all metrics, highlighting its generalizability and reliability. More importantly, it delivers highly consistent evaluation results across 12 LLMs (0.967 Pearson correlation against MMLU-Pro), while taking only $0.005 and 0.38 minutes per sample.