Zobrazeno 1 - 10
of 148
pro vyhledávání: '"Wen Zhihua"'
Publikováno v:
Jixie qiangdu, Pp 555-561 (2023)
A type of two-degree-of-freedom vibration system with bilateral nonlinear constraints is established. Through the fourth-order Runge-Kutta numerical algorithm, the dynamic characteristics of the p/1 periodic motion of the system under low frequency e
Externí odkaz:
https://doaj.org/article/399bd8e181df400b8031b0503a608985
Autor:
Fang, Xinyue, Huang, Zhen, Tian, Zhiliang, Fang, Minghui, Pan, Ziyi, Fang, Quntian, Wen, Zhihua, Pan, Hengyue, Li, Dongsheng
LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text ge
Externí odkaz:
http://arxiv.org/abs/2409.11283
Autor:
Zhang Huihua, Chen Qi, Yang Qianting, Zhang Mingxia, Dai Youchao, Cai Yi, Wen Zhihua, Chen Wenbin, Tan Yaoju, Guan Ping, Deng Guofang, Chen Xinchun
Publikováno v:
生物医学转化, Vol 2, Iss 2, Pp 91-98 (2021)
Objective To explore the diagnostic value of cell surface molecule CD161 by flow cytometrytechnology, and to establish deep learning networks that can distinguish sputum smear-negative pulmonary tuber‐culosis, sputum smear-negative IGRA positive/ne
Externí odkaz:
https://doaj.org/article/cdafb9ffb8204dd6ae6b8af22308b0c4
Publikováno v:
Rice Science, Vol 26, Iss 5, Pp 331-338 (2019)
To identify stable quantitative trait loci (QTLs) responsible for sheath blight resistance, a recombinant inbred line mapping population consisting of 219 lines was developed by crossing Lemont and Yangdao 4. Average disease rating, average lesion le
Externí odkaz:
https://doaj.org/article/8b3fb855b76446bc875601ecaf870364
Autor:
Wen, Zhihua, Tian, Zhiliang, Jian, Zexin, Huang, Zhen, Ke, Pei, Gao, Yifu, Huang, Minlie, Li, Dongsheng
Large Language Models (LLMs) are widely used for knowledge-seeking yet suffer from hallucinations. The knowledge boundary (KB) of an LLM limits its factual understanding, beyond which it may begin to hallucinate. Investigating the perception of LLMs'
Externí odkaz:
http://arxiv.org/abs/2405.14383
Temporal knowledge graph question answering (TKGQA) poses a significant challenge task, due to the temporal constraints hidden in questions and the answers sought from dynamic structured knowledge. Although large language models (LLMs) have made cons
Externí odkaz:
http://arxiv.org/abs/2402.16568
Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neural machine translation (UNMT) methods, including back-translation, tra
Externí odkaz:
http://arxiv.org/abs/2401.05596
Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on multiple NLP tasks, including story generation, it is challenging to ge
Externí odkaz:
http://arxiv.org/abs/2310.05388
Autor:
Guo, Chunxi, Tian, Zhiliang, Tang, Jintao, Li, Shasha, Wen, Zhihua, Wang, Kaixuan, Wang, Ting
Text-to-SQL aims at generating SQL queries for the given natural language questions and thus helping users to query databases. Prompt learning with large language models (LLMs) has emerged as a recent approach, which designs prompts to lead LLMs to u
Externí odkaz:
http://arxiv.org/abs/2307.05074
Autor:
Guo, Chunxi, Tian, Zhiliang, Tang, Jintao, Wang, Pancheng, Wen, Zhihua, Yang, Kang, Wang, Ting
Text-to-SQL is a task that converts a natural language question into a structured query language (SQL) to retrieve information from a database. Large language models (LLMs) work well in natural language generation tasks, but they are not specifically
Externí odkaz:
http://arxiv.org/abs/2304.13301