Výsledky vyhledávání

Report

Searching for Best Practices in Retrieval-Augmented Generation

Autor: Wang, Xiaohua, Wang, Zhenghua, Gao, Xuan, Zhang, Feiran, Wu, Yixin, Xu, Zhibo, Shi, Tianyuan, Wang, Zhengyuan, Li, Shizheng, Qian, Qi, Yin, Ruicheng, Lv, Changze, Zheng, Xiaoqing, Huang, Xuanjing

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been pro

Externí odkaz: http://arxiv.org/abs/2407.01219

Zobrazit plný text záznamu

Report

Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement

Autor: Huang, Zisu, Wang, Xiaohua, Zhang, Feiran, Xu, Zhibo, Zhang, Cenyuan, Zheng, Xiaoqing, Huang, Xuanjing

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full potential

Externí odkaz: http://arxiv.org/abs/2407.01461

Zobrazit plný text záznamu

Report

Towards Biologically Plausible Computing: A Comprehensive Comparison

Autor: Lv, Changze, Gu, Yufei, Guo, Zhengkang, Xu, Zhibo, Wu, Yixin, Zhang, Feiran, Shi, Tianyuan, Wang, Zhenghua, Yin, Ruicheng, Shang, Yu, Zhong, Siqi, Wang, Xiaohua, Wu, Muling, Liu, Wenhao, Li, Tianlong, Zhu, Jianhao, Zhang, Cenyuan, Ling, Zixuan, Zheng, Xiaoqing

Backpropagation is a cornerstone algorithm in training neural networks for supervised learning, which uses a gradient descent method to update network weights by minimizing the discrepancy between actual and desired outputs. Despite its pivotal role

Externí odkaz: http://arxiv.org/abs/2406.16062

Zobrazit plný text záznamu