Zobrazeno 1 - 10
of 396
pro vyhledávání: '"Zhang, TianHua"'
Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies on subgraph
Externí odkaz:
http://arxiv.org/abs/2410.18415
Query rewriting is a crucial technique for passage retrieval in open-domain conversational question answering (CQA). It decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers. Existing methods attem
Externí odkaz:
http://arxiv.org/abs/2406.10991
Autor:
Wang, Hongru, Xue, Boyang, Zhou, Baohang, Zhang, Tianhua, Wang, Cunxiang, Chen, Guanhua, Wang, Huimin, Wong, Kam-fai
Retrieve-then-read and generate-then-read are two typical solutions to handle unknown and known questions in open-domain question-answering, while the former retrieves necessary external knowledge and the later prompt the large language models to gen
Externí odkaz:
http://arxiv.org/abs/2402.13514
Autor:
Zhang, Tianhua, Ge, Jiaxin, Luo, Hongyin, Chuang, Yung-Sung, Gao, Mingye, Gong, Yuan, Wu, Xixin, Kim, Yoon, Meng, Helen, Glass, James
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic reasoning, nat
Externí odkaz:
http://arxiv.org/abs/2309.10814
Autor:
Luo, Hongyin, Chuang, Yung-Sung, Gong, Yuan, Zhang, Tianhua, Kim, Yoon, Wu, Xixin, Fox, Danny, Meng, Helen, Glass, James
Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAI
Externí odkaz:
http://arxiv.org/abs/2305.15225
Autor:
Zhang, Tianhua, Luo, Hongyin, Chuang, Yung-Sung, Fang, Wei, Gaitskell, Luc, Hartvigsen, Thomas, Wu, Xixin, Fox, Danny, Meng, Helen, Glass, James
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natura
Externí odkaz:
http://arxiv.org/abs/2304.03728
Publikováno v:
In Inorganica Chimica Acta 24 January 2025 575
Autor:
Sun, Mingyao, Zhang, Tianhua
Publikováno v:
IIMBG Journal of Sustainable Business and Innovation, 2023, Vol. 1, Issue 1, pp. 39-57.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/IJSBI-05-2023-0027
Autor:
Peng, Xuanbei, Luo, Yongjin, Zhang, Tianhua, Deng, Jinxiu, Zhou, Yanliang, Li, Jiaxin, Ni, Jun, Lin, Bingyu, Lin, Jianxin, Wu, Dongshuang, Zheng, Lirong, Wang, Xiuyun, Jiang, Lilong
Publikováno v:
In Chemical Engineering Science 15 June 2024 292
Autor:
Zhang, Tianhua, Hu, Haihui, Li, Jiaxin, Gao, Yinglong, Li, Lingling *, Zhang, Mingyuan, Peng, Xuanbei, Zhou, Yanliang, Ni, Jun, Lin, Bingyu, Lin, Jianxin, Zhu, Bing, Wu, Dongshuang, Zhang, Linjie, Han, Lili, Zheng, Lirong, Wang, Xiuyun *, Jiang, Lilong *
Publikováno v:
In Chinese Journal of Catalysis May 2024 60:209-218