no code implementations • COLING 2022 • Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu
The human recognition system has presented the remarkable ability to effortlessly learn novel knowledge from only a few trigger events based on prior knowledge, which is called insight learning.
1 code implementation • 17 Feb 2024 • Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang
In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG).
1 code implementation • 26 Nov 2023 • Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Zhaohui Wy, Dawei He, Peng Cheng, Zhonghao Wang, Haiying Deng
These techniques encompass the use of directed hallucination induction and strategies that deliberately alter authentic text to produce hallucinations.
no code implementations • 25 May 2023 • Aakas Zhiyuli, Yanfang Chen, Xuan Zhang, Xun Liang
At the same time, based on different evaluation schemes for book recommendation tasks and the existing classic recommendation models, this paper discusses the advantages and disadvantages of the BookGPT in book recommendation scenarios and analyzes the opportunities and improvement directions for subsequent LLMs in these scenarios.
no code implementations • 22 Oct 2020 • Xun Liang, Qingfeng Guan, Keith C. Clarke, Shishi Liu, Bingyu Wang, Yao Yao
The change complexity lies in the detailed scale of high granularity data, and in the geometric units used to simulate the change.
Computers and Society
no code implementations • 16 Mar 2018 • Xun Liang
In addition, previous models are unable to simulate the urban dynamics in Xiongan New Area.