Zobrazeno 1 - 10
of 67
pro vyhledávání: '"Yin, Qingyu"'
Autor:
Yin, Qingyu, Leong, Chak Tou, Zhang, Hongbo, Zhu, Minjun, Yan, Hanqi, Zhang, Qiang, He, Yulan, Li, Wenjie, Wang, Jun, Zhang, Yue, Yang, Linyi
The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved notable success
Externí odkaz:
http://arxiv.org/abs/2411.07618
Autor:
Jin, Yilun, Li, Zheng, Zhang, Chenwei, Cao, Tianyu, Gao, Yifan, Jayarao, Pratik, Li, Mao, Liu, Xin, Sarkhel, Ritesh, Tang, Xianfeng, Wang, Haodong, Wang, Zhengyang, Xu, Wenju, Yang, Jingfeng, Yin, Qingyu, Li, Xian, Nigam, Priyanka, Xu, Yi, Chen, Kai, Yang, Qiang, Jiang, Meng, Yin, Bing
Online shopping is a complex multi-task, few-shot learning problem with a wide and evolving range of entities, relations, and tasks. However, existing models and benchmarks are commonly tailored to specific tasks, falling short of capturing the full
Externí odkaz:
http://arxiv.org/abs/2410.20745
Autor:
Yin, Qingyu, He, Xuzheng, Deng, Luoao, Leong, Chak Tou, Wang, Fan, Yan, Yanzhao, Shen, Xiaoyu, Zhang, Qiang
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the model to ad
Externí odkaz:
http://arxiv.org/abs/2410.04691
Autor:
Wang, Kuan, Bukharin, Alexander, Jiang, Haoming, Yin, Qingyu, Wang, Zhengyang, Zhao, Tuo, Shang, Jingbo, Zhang, Chao, Yin, Bing, Li, Xian, Chen, Jianshu, Li, Shiyang
Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models trained on open-source IFT datasets only have the ability to follow ins
Externí odkaz:
http://arxiv.org/abs/2409.13733
Autor:
Gan, Chengguang, Yin, Qingyu, He, Xinyang, Wei, Hanjun, Liang, Yunhao, Lim, Younghun, Wang, Shijian, Huang, Hexiang, Zhang, Qinghao, Ni, Shiwen, Mori, Tatsunori
The Mutual Reinforcement Effect (MRE) represents a promising avenue in information extraction and multitasking research. Nevertheless, its applicability has been constrained due to the exclusive availability of MRE mix datasets in Japanese, thereby l
Externí odkaz:
http://arxiv.org/abs/2407.10953
Autor:
Xu, Baixuan, Wang, Weiqi, Shi, Haochen, Ding, Wenxuan, Jing, Huihao, Fang, Tianqing, Bai, Jiaxin, Liu, Xin, Yu, Changlong, Li, Zheng, Luo, Chen, Yin, Qingyu, Yin, Bing, Chen, Long, Song, Yangqiu
Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with
Externí odkaz:
http://arxiv.org/abs/2406.10701
Autor:
Ding, Wenxuan, Wang, Weiqi, Kwok, Sze Heng Douglas, Liu, Minghao, Fang, Tianqing, Bai, Jiaxin, Liu, Xin, Yu, Changlong, Li, Zheng, Luo, Chen, Yin, Qingyu, Yin, Bing, He, Junxian, Song, Yangqiu
Enhancing Language Models' (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, previous approaches that distill intentions from LMs often fail to gene
Externí odkaz:
http://arxiv.org/abs/2406.10173
Autor:
Liu, Fenglin, Li, Zheng, Zhou, Hongjian, Yin, Qingyu, Yang, Jingfeng, Tang, Xianfeng, Luo, Chen, Zeng, Ming, Jiang, Haoming, Gao, Yifan, Nigam, Priyanka, Nag, Sreyashi, Yin, Bing, Hua, Yining, Zhou, Xuan, Rohanian, Omid, Thakur, Anshul, Clifton, Lei, Clifton, David A.
The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involv
Externí odkaz:
http://arxiv.org/abs/2405.00716
Autor:
Chen, Xiusi, Wen, Hongzhi, Nag, Sreyashi, Luo, Chen, Yin, Qingyu, Li, Ruirui, Li, Zheng, Wang, Wei
With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional AI (CAI) ha
Externí odkaz:
http://arxiv.org/abs/2403.18341
Autor:
Wei, Tianxin, Jin, Bowen, Li, Ruirui, Zeng, Hansi, Wang, Zhengyang, Sun, Jianhui, Yin, Qingyu, Lu, Hanqing, Wang, Suhang, He, Jingrui, Tang, Xianfeng
Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Our daily choices, especially in domains like fashion and retail, are su
Externí odkaz:
http://arxiv.org/abs/2403.10667