C$^2$LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation
This addresses the issue of unreliable evaluation for researchers and developers due to data contamination, though it is incremental as it builds on existing benchmark methods.
The paper tackles the problem of data contamination in large language model evaluation by introducing C^2LEVA, a bilingual benchmark with systematic contamination prevention, and shows its effectiveness through evaluation of 15 models across 22 tasks.
Recent advances in large language models (LLMs) have shown significant promise, yet their evaluation raises concerns, particularly regarding data contamination due to the lack of access to proprietary training data. To address this issue, we present C$^2$LEVA, a comprehensive bilingual benchmark featuring systematic contamination prevention. C$^2$LEVA firstly offers a holistic evaluation encompassing 22 tasks, each targeting a specific application or ability of LLMs, and secondly a trustworthy assessment due to our contamination-free tasks, ensured by a systematic contamination prevention strategy that fully automates test data renewal and enforces data protection during benchmark data release. Our large-scale evaluation of 15 open-source and proprietary models demonstrates the effectiveness of C$^2$LEVA.