Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Ma, Haodi"'
Autor:
Hao, Shibo, Gu, Yi, Luo, Haotian, Liu, Tianyang, Shao, Xiyan, Wang, Xinyuan, Xie, Shuhua, Ma, Haodi, Samavedhi, Adithya, Gao, Qiyue, Wang, Zhen, Hu, Zhiting
Generating accurate step-by-step reasoning is essential for Large Language Models (LLMs) to address complex problems and enhance robustness and interpretability. Despite the flux of research on developing advanced reasoning approaches, systematically
Externí odkaz:
http://arxiv.org/abs/2404.05221
Large language model (LLM) has marked a pivotal moment in the field of machine learning and deep learning. Recently its capability for query planning has been investigated, including both single-modal and multi-modal queries. However, there is no wor
Externí odkaz:
http://arxiv.org/abs/2403.13597
Knowledge Graph (KG)-to-Text Generation has seen recent improvements in generating fluent and informative sentences which describe a given KG. As KGs are widespread across multiple domains and contain important entity-relation information, and as tex
Externí odkaz:
http://arxiv.org/abs/2308.06975
Recent works in neural knowledge graph inference attempt to combine logic rules with knowledge graph embeddings to benefit from prior knowledge. However, they usually cannot avoid rule grounding, and injecting a diverse set of rules has still not bee
Externí odkaz:
http://arxiv.org/abs/2308.03269
Large language models (LLMs) have shown remarkable reasoning capabilities, especially when prompted to generate intermediate reasoning steps (e.g., Chain-of-Thought, CoT). However, LLMs can still struggle with problems that are easy for humans, such
Externí odkaz:
http://arxiv.org/abs/2305.14992
Autor:
Ma, Haodi, Wang, Daisy Zhe
Knowledge graphs (KG) have served as the key component of various natural language processing applications. Commonsense knowledge graphs (CKG) are a special type of KG, where entities and relations are composed of free-form text. However, previous wo
Externí odkaz:
http://arxiv.org/abs/2301.01172
Autor:
Ma, Haodi1 (AUTHOR), Shi, LinLin2 (AUTHOR), Zheng, Jiayu1 (AUTHOR), Zeng, Li1 (AUTHOR), Chen, Youyou1 (AUTHOR), Zhang, Shunshun1 (AUTHOR), Tang, Siya1 (AUTHOR), Qu, Zhifeng3 (AUTHOR), Xiong, Xin4 (AUTHOR), Zheng, Xuewei1,5 (AUTHOR) xwzheng0529@163.com, Yin, Qinan1,5 (AUTHOR) qinanyin@haust.edu.cn
Publikováno v:
BMC Cancer. 10/1/2024, Vol. 24 Issue 1, p1-17. 17p.
Many recent approaches of passage retrieval are using dense embeddings generated from deep neural models, called "dense passage retrieval". The state-of-the-art end-to-end dense passage retrieval systems normally deploy a deep neural model followed b
Externí odkaz:
http://arxiv.org/abs/2205.00970
Autor:
Zheng, Xuewei, Zhang, ShunShun, Ma, HaoDi, Dong, Yirui, Zheng, Jiayu, Zeng, Li, Liu, Jiangbo, Dai, Yanzhenzi, Yin, Qinan
Publikováno v:
In Molecular and Cellular Endocrinology 1 October 2024 592
Autor:
Yin, Qinan1 (AUTHOR), Ma, Haodi1 (AUTHOR), Dong, Yirui1 (AUTHOR), Zhang, Shunshun1 (AUTHOR), Wang, Junxiang2 (AUTHOR), Liang, Jing3 (AUTHOR), Mao, Longfei4 (AUTHOR), Zeng, Li1 (AUTHOR), Xiong, Xin5 (AUTHOR), Chen, Xingang1 (AUTHOR), Wang, Jingjing1 (AUTHOR), Zheng, Xuewei1 (AUTHOR) xwzheng0529@163.com
Publikováno v:
Journal of Translational Medicine. 1/20/2024, Vol. 22 Issue 1, p1-16. 16p.