Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation

TL;DR

This paper reviews recent progress in transitioning from static to dynamic benchmarking of large language models to better address data contamination issues, proposing design principles and analyzing current methods.

Contribution

It provides a comprehensive analysis of static and dynamic benchmarks, identifies gaps, and proposes principles for effective dynamic benchmarking of LLMs.

Findings

Static benchmarks have limitations in contamination detection.

Dynamic benchmarks offer improved contamination mitigation.

A set of design principles for dynamic benchmarking is proposed.

Abstract

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has undergone a transformation from static to dynamic benchmarking. In this work, we conduct an in-depth analysis of existing static to dynamic benchmarking methods aimed at reducing data contamination risks. We first examine methods that enhance static benchmarks and identify their inherent limitations. We then highlight a critical gap-the lack of standardized criteria for evaluating dynamic benchmarks. Based on this observation, we propose a series of optimal design principles for dynamic benchmarking and analyze the limitations of existing dynamic benchmarks. This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.