Zobrazeno 1 - 10
of 903
pro vyhledávání: '"Wang, Shijin"'
Autor:
Hong, Bin, Wu, Jinze, Liu, Jiayu, Ding, Liang, Sha, Jing, Zhang, Kai, Wang, Shijin, Huang, Zhenya
In recent years, the breakthrough of Large Language Models (LLMs) offers new ideas for achieving universal methods on graph data. The common practice of converting graphs into natural language for LLMs, which refers to graph flattening, exhibits good
Externí odkaz:
http://arxiv.org/abs/2409.14880
Autor:
Huang, Yuqing, Zhang, Rongyang, He, Xuesong, Zhi, Xuyang, Wang, Hao, Li, Xin, Xu, Feiyang, Liu, Deguang, Liang, Huadong, Li, Yi, Cui, Jian, Liu, Zimu, Wang, Shijin, Hu, Guoping, Liu, Guiquan, Liu, Qi, Lian, Defu, Chen, Enhong
There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess the performance of LLMs across a spectrum of chemical tasks varying in t
Externí odkaz:
http://arxiv.org/abs/2409.13989
Autor:
Wu, Dayong, Li, Jiaqi, Wang, Baoxin, Zhao, Honghong, Xue, Siyuan, Yang, Yanjie, Chang, Zhijun, Zhang, Rui, Qian, Li, Wang, Bo, Wang, Shijin, Zhang, Zhixiong, Hu, Guoping
Large language models (LLMs) have shown remarkable achievements across various language tasks.To enhance the performance of LLMs in scientific literature services, we developed the scientific literature LLM (SciLit-LLM) through pre-training and super
Externí odkaz:
http://arxiv.org/abs/2408.06574
Autor:
Wang, Fei, Gao, Weibo, Liu, Qi, Li, Jiatong, Zhao, Guanhao, Zhang, Zheng, Huang, Zhenya, Zhu, Mengxiao, Wang, Shijin, Tong, Wei, Chen, Enhong
Cognitive diagnosis has been developed for decades as an effective measurement tool to evaluate human cognitive status such as ability level and knowledge mastery. It has been applied to a wide range of fields including education, sport, psychologica
Externí odkaz:
http://arxiv.org/abs/2407.05458
Autor:
Zhou, Kun, Zhang, Beichen, Wang, Jiapeng, Chen, Zhipeng, Zhao, Wayne Xin, Sha, Jing, Sheng, Zhichao, Wang, Shijin, Wen, Ji-Rong
Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale math-related texts for pre-training, or relies on stronger LLMs (\eg
Externí odkaz:
http://arxiv.org/abs/2405.14365
Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropri
Externí odkaz:
http://arxiv.org/abs/2405.06232
Autor:
Liu, Qi, Zhuang, Yan, Bi, Haoyang, Huang, Zhenya, Huang, Weizhe, Li, Jiatong, Yu, Junhao, Liu, Zirui, Hu, Zirui, Hong, Yuting, Pardos, Zachary A., Ma, Haiping, Zhu, Mengxiao, Wang, Shijin, Chen, Enhong
Computerized Adaptive Testing (CAT) provides an efficient and tailored method for assessing the proficiency of examinees, by dynamically adjusting test questions based on their performance. Widely adopted across diverse fields like education, healthc
Externí odkaz:
http://arxiv.org/abs/2404.00712
Cognitive diagnosis models have been widely used in different areas, especially intelligent education, to measure users' proficiency levels on knowledge concepts, based on which users can get personalized instructions. As the measurement is not alway
Externí odkaz:
http://arxiv.org/abs/2403.14676
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale back
Externí odkaz:
http://arxiv.org/abs/2403.06071
Since the release of ChatGPT, generative models have achieved tremendous success and become the de facto approach for various NLP tasks. However, its application in the field of input methods remains under-explored. Many neural network approaches hav
Externí odkaz:
http://arxiv.org/abs/2311.01166