no code implementations • ACL 2022 • Tingchen Fu, Xueliang Zhao, Chongyang Tao, Ji-Rong Wen, Rui Yan
Knowledge-grounded conversation (KGC) shows great potential in building an engaging and knowledgeable chatbot, and knowledge selection is a key ingredient in it.
no code implementations • 21 Feb 2024 • Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong
Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs).
1 code implementation • 3 Sep 2023 • Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, Shuming Shi
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
no code implementations • 22 Oct 2022 • Xueliang Zhao, Lemao Liu, Tingchen Fu, Shuming Shi, Dongyan Zhao, Rui Yan
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications.
no code implementations • 22 Oct 2022 • Xueliang Zhao, Tingchen Fu, Chongyang Tao, Rui Yan
Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response.
no code implementations • NAACL 2022 • Xueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu, Dongyan Zhao, Rui Yan
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses.
1 code implementation • 6 Apr 2022 • Tingchen Fu, Xueliang Zhao, Chongyang Tao, Ji-Rong Wen, Rui Yan
In this work, we introduce personal memory into knowledge selection in KGC to address the personalization issue.