2 papers
cs.AI2025
Auto-Prompt Ensemble for LLM Judge
Jiajie Li, Huayi Zhang, Peng Lin +2
We present a novel framework that improves the reliability of LLM judges by selectively augmenting LLM with auxiliary evaluation dimensions. Existing LLM judges often miss crucial…
cs.LG2025
ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
Yang Wu, Huayi Zhang, Yizheng Jiao +6
Instruction tuning has underscored the significant potential of large language models (LLMs) in producing more human controllable and effective outputs in various domains. In this…