Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Qiao, Shuofei"'
Autor:
Qiao, Shuofei, Fang, Runnan, Qiu, Zhisong, Wang, Xiaobin, Zhang, Ningyu, Jiang, Yong, Xie, Pengjun, Huang, Fei, Chen, Huajun
Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein decomposing complex problems into executable workflows is a crucial s
Externí odkaz:
http://arxiv.org/abs/2410.07869
Autor:
Wang, Mengru, Yao, Yunzhi, Xu, Ziwen, Qiao, Shuofei, Deng, Shumin, Wang, Peng, Chen, Xiang, Gu, Jia-Chen, Jiang, Yong, Xie, Pengjun, Huang, Fei, Chen, Huajun, Zhang, Ningyu
Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utiliz
Externí odkaz:
http://arxiv.org/abs/2407.15017
Autor:
Qiao, Shuofei, Fang, Runnan, Zhang, Ningyu, Zhu, Yuqi, Chen, Xiang, Deng, Shumin, Jiang, Yong, Xie, Pengjun, Huang, Fei, Chen, Huajun
Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in glob
Externí odkaz:
http://arxiv.org/abs/2405.14205
Autor:
Zhu, Yuqi, Qiao, Shuofei, Ou, Yixin, Deng, Shumin, Zhang, Ningyu, Lyu, Shiwei, Shen, Yue, Liang, Lei, Gu, Jinjie, Chen, Huajun
Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inad
Externí odkaz:
http://arxiv.org/abs/2403.03101
Autor:
Ou, Yixin, Zhang, Ningyu, Gui, Honghao, Xu, Ziwen, Qiao, Shuofei, Xue, Yida, Fang, Runnan, Liu, Kangwei, Li, Lei, Bi, Zhen, Zheng, Guozhou, Chen, Huajun
In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing approaches
Externí odkaz:
http://arxiv.org/abs/2402.03049
Autor:
Qiao, Shuofei, Zhang, Ningyu, Fang, Runnan, Luo, Yujie, Zhou, Wangchunshu, Jiang, Yuchen Eleanor, Lv, Chengfei, Chen, Huajun
Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-repro
Externí odkaz:
http://arxiv.org/abs/2401.05268
Autor:
Zhu, Yuqi, Wang, Xiaohan, Chen, Jing, Qiao, Shuofei, Ou, Yixin, Yao, Yunzhi, Deng, Shumin, Chen, Huajun, Zhang, Ningyu
This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experiments across eight diverse datasets, focusing on four representative tas
Externí odkaz:
http://arxiv.org/abs/2305.13168
Tools serve as pivotal interfaces that enable humans to understand and reshape the environment. With the advent of foundation models, AI systems can utilize tools to expand their capabilities and interact with the real world. Existing tool learning m
Externí odkaz:
http://arxiv.org/abs/2305.13068
Autor:
Gui, Honghao, Qiao, Shuofei, Zhang, Jintian, Ye, Hongbin, Sun, Mengshu, Liang, Lei, Pan, Jeff Z., Chen, Huajun, Zhang, Ningyu
Large language models can perform well on general natural language tasks, but their effectiveness is still suboptimal for information extraction (IE). Recent works indicate that the main reason lies in the lack of extensive data on IE instructions. N
Externí odkaz:
http://arxiv.org/abs/2305.11527
Autor:
Chen, Xiang, Li, Lei, Qiao, Shuofei, Zhang, Ningyu, Tan, Chuanqi, Jiang, Yong, Huang, Fei, Chen, Huajun
Cross-domain NER is a challenging task to address the low-resource problem in practical scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the ta
Externí odkaz:
http://arxiv.org/abs/2301.10410