Zobrazeno 1 - 10
of 51 936
pro vyhledávání: '"Zhang, Qi"'
Autor:
Fu, Jia, Qin, Xiaoting, Yang, Fangkai, Wang, Lu, Zhang, Jue, Lin, Qingwei, Chen, Yubo, Zhang, Dongmei, Rajmohan, Saravan, Zhang, Qi
Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) systems. To address the challenges of hyper-parameter optimization and onl
Externí odkaz:
http://arxiv.org/abs/2406.19251
Autor:
Huang, Caishuang, Zhao, Wanxu, Zheng, Rui, Lv, Huijie, Dou, Shihan, Li, Sixian, Wang, Xiao, Zhou, Enyu, Ye, Junjie, Yang, Yuming, Gui, Tao, Zhang, Qi, Huang, Xuanjing
As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks (i.e., effo
Externí odkaz:
http://arxiv.org/abs/2406.18118
Autor:
Zhang, Qi S.
Using a size condition of the sharp log Sobolev functional (log entropy) near infinity only, we prove a rigidity result for ancient Ricci flows without sign condition on the curvatures. The result is also related to the problem of identifying type II
Externí odkaz:
http://arxiv.org/abs/2406.17179
We introduce an innovative and mathematically rigorous definition for computing common information from multi-view data, drawing inspiration from G\'acs-K\"orner common information in information theory. Leveraging this definition, we develop a novel
Externí odkaz:
http://arxiv.org/abs/2406.15043
Publikováno v:
LREC-COLING. (2024) 14407-14417
We present SciDMT, an enhanced and expanded corpus for scientific mention detection, offering a significant advancement over existing related resources. SciDMT contains annotated scientific documents for datasets (D), methods (M), and tasks (T). The
Externí odkaz:
http://arxiv.org/abs/2406.14756
Autor:
An, Kaikai, Yang, Fangkai, Li, Liqun, Lu, Junting, Cheng, Sitao, Wang, Lu, Zhao, Pu, Cao, Lele, Lin, Qingwei, Rajmohan, Saravan, Zhang, Dongmei, Zhang, Qi
Current question answering systems leveraging retrieval augmented generation perform well in answering factoid questions but face challenges with non-factoid questions, particularly how-to queries requiring detailed step-by-step instructions and expl
Externí odkaz:
http://arxiv.org/abs/2406.13372
Autor:
Jiang, Yu-Xiao, Shao, Sen, Xia, Wei, Denner, M. Michael, Ingham, Julian, Hossain, Md Shafayat, Qiu, Qingzheng, Zheng, Xiquan, Chen, Hongyu, Cheng, Zi-Jia, Yang, Xian P., Kim, Byunghoon, Yin, Jia-Xin, Zhang, Songbo, Litskevich, Maksim, Zhang, Qi, Cochran, Tyler A., Peng, Yingying, Chang, Guoqing, Guo, Yanfeng, Thomale, Ronny, Neupert, Titus, Hasan, M. Zahid
Novel states of matter arise in quantum materials due to strong interactions among electrons. A nematic phase breaks the point group symmetry of the crystal lattice and is known to emerge in correlated materials. Here we report the observation of an
Externí odkaz:
http://arxiv.org/abs/2406.13702
This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former approach suff
Externí odkaz:
http://arxiv.org/abs/2406.12125
Autor:
Yang, Yuming, Zhao, Wantong, Huang, Caishuang, Ye, Junjie, Wang, Xiao, Zheng, Huiyuan, Nan, Yang, Wang, Yuran, Xu, Xueying, Huang, Kaixin, Zhang, Yunke, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost the
Externí odkaz:
http://arxiv.org/abs/2406.11192
Autor:
Bao, Rong, Zheng, Rui, Dou, Shihan, Wang, Xiao, Zhou, Enyu, Wang, Bo, Zhang, Qi, Ding, Liang, Tao, Dacheng
In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and societal values
Externí odkaz:
http://arxiv.org/abs/2406.11190