Zobrazeno 1 - 10
of 3 368
pro vyhledávání: '"Yu, Ge"'
Fact verification tasks aim to identify the integrity of textual contents according to the truthful corpus. Existing fact verification models usually build a fully connected reasoning graph, which regards claim-evidence pairs as nodes and connects th
Externí odkaz:
http://arxiv.org/abs/2405.10481
Large language models (LLMs) require lengthy prompts as the input context to produce output aligned with user intentions, a process that incurs extra costs during inference. In this paper, we propose the Gist COnditioned deCOding (Gist-COCO) model, i
Externí odkaz:
http://arxiv.org/abs/2402.16058
The web contains large-scale, diverse, and abundant information to satisfy the information-seeking needs of humans. Through meticulous data collection, preprocessing, and curation, webpages can be used as a fundamental data resource for language mode
Externí odkaz:
http://arxiv.org/abs/2402.14652
Autor:
Xu, Zhipeng, Liu, Zhenghao, Liu, Yibin, Xiong, Chenyan, Yan, Yukun, Wang, Shuo, Yu, Shi, Liu, Zhiyuan, Yu, Ge
Retrieval Augmented Generation (RAG) has introduced a new paradigm for Large Language Models (LLMs), aiding in the resolution of knowledge-intensive tasks. However, current RAG models position LLMs as passive knowledge receptors, thereby restricting
Externí odkaz:
http://arxiv.org/abs/2402.13547
Autor:
Liu, Pengjie, Liu, Zhenghao, Yi, Xiaoyuan, Yang, Liner, Wang, Shuo, Gu, Yu, Yu, Ge, Xie, Xing, Yang, Shuang-hua
Most existing Legal Judgment Prediction (LJP) models focus on discovering the legal triggers in the criminal fact description. However, in real-world scenarios, a professional judge not only needs to assimilate the law case experience that thrives on
Externí odkaz:
http://arxiv.org/abs/2401.15371
Autor:
Wang, Zhigang, Yang, Hangyu, Wang, Ning, Xu, Chuanfei, Nie, Jie, Wei, Zhiqiang, Gu, Yu, Yu, Ge
In the last decade, Convolutional Neural Network with a multi-layer architecture has advanced rapidly. However, training its complex network is very space-consuming, since a lot of intermediate data are preserved across layers, especially when proces
Externí odkaz:
http://arxiv.org/abs/2401.11471
Transformer-based models are becoming deeper and larger recently. For better scalability, an underlying training solution in industry is to split billions of parameters (tensors) into many tasks and then run them across homogeneous accelerators (e.g.
Externí odkaz:
http://arxiv.org/abs/2401.11469
Publikováno v:
Phys. Rev. B 108, 235147 (2023)
Superconductors (SCs) with nontrivial topological band structures in the normal state have been discovered recently in bulk materials. When such SCs are made into thin films, quantum tunneling and Cooper pairing take place between the topological sur
Externí odkaz:
http://arxiv.org/abs/2312.10453
Autor:
Chen, Chaoyi, Gao, Dechao, Zhang, Yanfeng, Wang, Qiange, Fu, Zhenbo, Zhang, Xuecang, Zhu, Junhua, Gu, Yu, Yu, Ge
Existing Graph Neural Network (GNN) training frameworks have been designed to help developers easily create performant GNN implementations. However, most existing GNN frameworks assume that the input graphs are static, but ignore that most real-world
Externí odkaz:
http://arxiv.org/abs/2312.02473
Many Graph Neural Network (GNN) training systems have emerged recently to support efficient GNN training. Since GNNs embody complex data dependencies between training samples, the training of GNNs should address distinct challenges different from DNN
Externí odkaz:
http://arxiv.org/abs/2311.13279