3 papers
cs.CL2026
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
Ruijie Hou, Yueyang Jiao, Zhao Wang +1
Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized. \textbf{Contamination mitigation evaluation} intervenes in t…
cs.CL2025
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models
Ruijie Hou, Yueyang Jiao, Hanxu Hu +4
The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benc…
cs.CL2023
CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
Wenhong Zhu, Hongkun Hao, Zhiwei He +6
We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessi…