Zobrazeno 1 - 10
of 420
pro vyhledávání: '"Zhu, Zhihao"'
Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in retrieval-augmente
Externí odkaz:
http://arxiv.org/abs/2404.16587
Autor:
Ma, Chang, Zhang, Junlei, Zhu, Zhihao, Yang, Cheng, Yang, Yujiu, Jin, Yaohui, Lan, Zhenzhong, Kong, Lingpeng, He, Junxian
Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A pri
Externí odkaz:
http://arxiv.org/abs/2401.13178
Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting the potent
Externí odkaz:
http://arxiv.org/abs/2312.10943
Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some adversarial atta
Externí odkaz:
http://arxiv.org/abs/2312.11571
Autor:
Huang, Yuzhen, Bai, Yuzhuo, Zhu, Zhihao, Zhang, Junlei, Zhang, Jinghan, Su, Tangjun, Liu, Junteng, Lv, Chuancheng, Zhang, Yikai, Lei, Jiayi, Fu, Yao, Sun, Maosong, He, Junxian
New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundatio
Externí odkaz:
http://arxiv.org/abs/2305.08322
Publikováno v:
Cailiao gongcheng, Vol 52, Iss 5, Pp 117-126 (2024)
The composition of high-damage-tolerance dual-phase TC21 (Ti-6Al-2Zr-2Sn-2Mo-2Nb-1.5Cr) were analyzed on the basis of the dual-cluster formula of Ti-6Al-4V, consisting of 13 α-Ti and 4 β-Ti unit. Its β-Ti unit is reduced from 5 to 4 compared with
Externí odkaz:
https://doaj.org/article/b07a4d88a469412bb55e3ec2669dd2ab
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications. In this work, we focus on the emerging but
Externí odkaz:
http://arxiv.org/abs/2211.08068
Autor:
Weng, Shuofeng, Yuan, Chaochun, He, Youguo, Shen, Jie, Chen, Long, Xu, Lizhang, Zhu, Zhihao, Yu, Qiuye, Sun, Zeyu
Publikováno v:
In Engineering Applications of Artificial Intelligence October 2024 136 Part B
Publikováno v:
In Journal of Ethnopharmacology 15 September 2024 331
Publikováno v:
In Construction and Building Materials 12 July 2024 435