1 citations · 1 across the 2 of their papers we have counts for
3 papers
cs.CL2026
Triviality Corrected Endogenous Reward
Xinda Wang, Zhengxu Hou, Yangshijie Zhang +6
Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or…
cs.CL2025★ 1 cited
TASE: Token Awareness and Structured Evaluation for Multilingual Language Models
Chenzhuo Zhao, Xinda Wang, Yue Huang +2
While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and struc…
cs.CL2025
PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
Chenzhuo Zhao, Ziqian Liu, Xinda Wang +2
Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate pro…