Teach2Eval: An Interaction-Driven LLMs Evaluation Method via Teaching Effectiveness
Yuhang Zhou · Xutian Chen · Yixin Cao · Yuchen Ni · Yu He · Siyu Tian · Xiang Liu · Yunwen Chen · Guangnan Ye · Xipeng Qiu · Hongfeng Chai
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Yuhang Zhou · Xutian Chen · Yixin Cao · Yuchen Ni · Yu He · Siyu Tian · Xiang Liu · Yunwen Chen · Guangnan Ye · Xipeng Qiu · Hongfeng Chai
Yuhang Zhou · Yixin Cao · Yuchen Ni · Shihan Dou · Xutian Chen · Ge Zhang · Xiang Liu · Guangnan Ye
Standard evaluators, such as reward models, compress diverse human judgments into a single scalar, conflating valid Subjective Preference with Cognitive Uncertainty. This structural mismatch often leads to brittle alignment and reward hacking. To address this, we propose PRISM which reinterprets...
Yanning Su · Yuhang Zhou · Yang Fang · Sen Liu · Guangnan Ye · Hongfeng Chai
Despite growing interest in NL2GQL, benchmarking progress has been constrained by the lack of resources that are simultaneously large-scale, cross-domain, and cross-dialect. To address this gap, we present GQLBench , a new benchmark built through an automated and scalable framework that integrate...