Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Xu, Yishi"'
Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and reliability conce
Externí odkaz:
http://arxiv.org/abs/2409.03274
Autor:
Gosal, Gurpreet, Xu, Yishi, Ramakrishnan, Gokul, Joshi, Rituraj, Sheinin, Avraham, Zhiming, Chen, Mishra, Biswajit, Vassilieva, Natalia, Hestness, Joel, Sengupta, Neha, Sahu, Sunil Kumar, Jia, Bokang, Pandit, Onkar, Katipomu, Satheesh, Kamboj, Samta, Ghosh, Samujjwal, Pal, Rahul, Mullah, Parvez, Doraiswamy, Soundar, Chami, Mohamed El Karim, Nakov, Preslav
We present an efficient method for adapting a monolingual Large Language Model (LLM) to another language, addressing challenges of catastrophic forgetting and tokenizer limitations. We focus this study on adapting Llama 2 to Arabic. Our two-stage app
Externí odkaz:
http://arxiv.org/abs/2407.12869
Autor:
Wang, Chaojie, Xu, Yishi, Peng, Zhong, Zhang, Chenxi, Chen, Bo, Wang, Xinrun, Feng, Lei, An, Bo
Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering. However, in the face of problems beyond the scope of knowledge, these LLMs tend to talk nonsense
Externí odkaz:
http://arxiv.org/abs/2401.00426
Autor:
Liu, Xinyang, Wang, Dongsheng, Fang, Bowei, Li, Miaoge, Duan, Zhibin, Xu, Yishi, Chen, Bo, Zhou, Mingyuan
For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the prompt tunin
Externí odkaz:
http://arxiv.org/abs/2303.09100
Embedded topic models are able to learn interpretable topics even with large and heavy-tailed vocabularies. However, they generally hold the Euclidean embedding space assumption, leading to a basic limitation in capturing hierarchical relations. To t
Externí odkaz:
http://arxiv.org/abs/2210.10625
Autor:
Wang, Dongsheng, Xu, Yishi, Li, Miaoge, Duan, Zhibin, Wang, Chaojie, Chen, Bo, Zhou, Mingyuan
We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling. Although embedded topic models (ETMs) and its variants have gained promising performance in text analysis, they mainly focus on mining w
Externí odkaz:
http://arxiv.org/abs/2209.14228
Autor:
Zhang, Chenxi1 (AUTHOR) xuyishi@stu.xidian.edu.cn, Xu, Yishi1 (AUTHOR), Chen, Wenchao1 (AUTHOR) chenwenchao@xidian.edu.cn, Chen, Bo1 (AUTHOR), Gao, Chang1 (AUTHOR), Liu, Hongwei1 (AUTHOR)
Publikováno v:
Remote Sensing. Jun2024, Vol. 16 Issue 12, p2199. 27p.
Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior beliefs su
Externí odkaz:
http://arxiv.org/abs/2110.14286
Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and
Externí odkaz:
http://arxiv.org/abs/2104.08419
Given the convenience of collecting information through online services, recommender systems now consume large scale data and play a more important role in improving user experience. With the recent emergence of Graph Neural Networks (GNNs), GNN-base
Externí odkaz:
http://arxiv.org/abs/2008.13517