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。
Zhuo Li · Pengyu Cheng · Zhechao Yu · FeifeiTong · Anningzhe Gao · Tsung-Hui Chang · Xiang Wan · erchao.zec · xiaoxi jiang · guanjunjiang
Haozhong Wang · Zhuo Li · Yibo Yang · He Zhao · Hongyuan Zha · Dandan Guo
The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on heuristic, instance-level assessments that neglect the gl...
Chongyuan Dai · Jinpeng Hu · Hongchang Shi · Zhuo Li · Dan Guo · Xun Yang · Meng Wang
Amidst a shortage of qualified mental health professionals, the integration of large language models (LLMs) into psychological applications offers a promising way to alleviate the growing burden of mental health disorders. Recent reasoning-augmented LLMs have achieved remarkable performance in ma...
Zhuo Li · Yupeng Zhang · Pengyu Cheng · Jiajun Song · Mengyu Zhou · Hao Li · Shujie Hu · Yu Qin · Erchao Zhao · xiaoxi jiang · Guanjun Jiang
Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection methods employ LLM-as-a-judge to verify LLM outputs against re...