← Search

Changhong Jin

2 accepted papers

2026

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement

AAAI 2026technical

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers pro

Cited by 0SourcePDFScholar
2025

DCR: Quantifying Data Contamination in LLMs Evaluation

EMNLP 2025

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and undermining genuine generalization assessment. This paper introd