Výsledky vyhledávání - "Tang Xiaojuan"

Akademický článek

The consequences of fermentation metabolism on the qualitative qualities and biological activity of fermented fruit and vegetable juices

Autor: Shah Saud, Tang Xiaojuan, Shah Fahad

Publikováno v: Food Chemistry: X, Vol 21, Iss , Pp 101209- (2024)

Fermentation of fruit and vegetable juices with probiotics is a novel nutritional approach with potential health benefits. Lactic acid fermentation-based biotransformation results in changes in the profile and nature of bioactive compounds and improv

Externí odkaz: https://doaj.org/article/7034ad77e87c4c219bf769d8f20f4b46

Zobrazit plný text záznamu

Report

Mars: Situated Inductive Reasoning in an Open-World Environment

Autor: Tang, Xiaojuan, Li, Jiaqi, Liang, Yitao, Zhu, Song-chun, Zhang, Muhan, Zheng, Zilong

Large Language Models (LLMs) trained on massive corpora have shown remarkable success in knowledge-intensive tasks. Yet, most of them rely on pre-stored knowledge. Inducing new general knowledge from a specific environment and performing reasoning wi

Externí odkaz: http://arxiv.org/abs/2410.08126

Zobrazit plný text záznamu

Report

Case-Based or Rule-Based: How Do Transformers Do the Math?

Autor: Hu, Yi, Tang, Xiaojuan, Yang, Haotong, Zhang, Muhan

Despite the impressive performance in a variety of complex tasks, modern large language models (LLMs) still have trouble dealing with some math problems that are simple and intuitive for humans, such as addition. While we can easily learn basic rules

Externí odkaz: http://arxiv.org/abs/2402.17709

Zobrazit plný text záznamu

Report

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

Autor: Tang, Xiaojuan, Zheng, Zilong, Li, Jiaqi, Meng, Fanxu, Zhu, Song-Chun, Liang, Yitao, Zhang, Muhan

The emergent few-shot reasoning capabilities of Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous successful applications, the underlying mechanism of such in-context

Externí odkaz: http://arxiv.org/abs/2305.14825

Zobrazit plný text záznamu

Report

RulE: Knowledge Graph Reasoning with Rule Embedding

Autor: Tang, Xiaojuan, Zhu, Song-Chun, Liang, Yitao, Zhang, Muhan

Knowledge graph (KG) reasoning is an important problem for knowledge graphs. In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}mbedding) to effectively leverage logical rules to enhance KG reasoning

Externí odkaz: http://arxiv.org/abs/2210.14905

Zobrazit plný text záznamu