Zobrazeno 1 - 10
of 144
pro vyhledávání: '"Yang Chenxu"'
The advent of large language models (LLMs) has significantly propelled the advancement of Role-Playing Agents (RPAs). However, current Role-Playing Agents predominantly focus on mimicking a character's fundamental attributes while neglecting the repl
Externí odkaz:
http://arxiv.org/abs/2411.02457
Autor:
Yang, Chenxu, Jia, Ruipeng, Gu, Naibin, Lin, Zheng, Chen, Siyuan, Pang, Chao, Yin, Weichong, Sun, Yu, Wu, Hua, Wang, Weiping
DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have endeavored to allev
Externí odkaz:
http://arxiv.org/abs/2409.14836
Autor:
Yang, Chenxu, Lin, Zheng, Tian, Chong, Pang, Liang, Wang, Lanrui, Tong, Zhengyang, Ho, Qirong, Cao, Yanan, Wang, Weiping
Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling, current a
Externí odkaz:
http://arxiv.org/abs/2407.05718
Autor:
Wang, Lanrui, Li, Jiangnan, Yang, Chenxu, Lin, Zheng, Tang, Hongyin, Liu, Huan, Huang, Xiaolei, Cao, Yanan, Wang, Jingang, Wang, Weiping
Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in dialogues, including expressing empathy and offering emotional support. Despite having access to commonsense
Externí odkaz:
http://arxiv.org/abs/2311.15316
Let $G$ be a graph and $S\subseteq V(G)$ with $|S|\geq 2$. Then the trees $T_1, T_2, \cdots, T_\ell$ in $G$ are \emph{internally disjoint Steiner trees} connecting $S$ (or $S$-Steiner trees) if $E(T_i) \cap E(T_j )=\emptyset$ and $V(T_i)\cap V(T_j)=S
Externí odkaz:
http://arxiv.org/abs/2310.16463
Autor:
Yang, Chenxu, Lin, Zheng, Wang, Lanrui, Tian, Chong, Pang, Liang, Li, Jiangnan, Ho, Qirong, Cao, Yanan, Wang, Weiping
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a human-like manner
Externí odkaz:
http://arxiv.org/abs/2310.08943
Publikováno v:
Fundamenta Informaticae, Volume 191, Issue 2 (July 8, 2024) fi:10788
Foucaud et al. recently introduced and initiated the study of a new graph-theoretic concept in the area of network monitoring. Given a graph $G=(V(G), E(G))$, a set $M \subseteq V(G)$ is a distance-edge-monitoring set if for every edge $e \in E(G)$,
Externí odkaz:
http://arxiv.org/abs/2301.02507
Autor:
Wang, Lanrui, Li, Jiangnan, Lin, Zheng, Meng, Fandong, Yang, Chenxu, Wang, Weiping, Zhou, Jie
Empathy, which is widely used in psychological counselling, is a key trait of everyday human conversations. Equipped with commonsense knowledge, current approaches to empathetic response generation focus on capturing implicit emotion within dialogue
Externí odkaz:
http://arxiv.org/abs/2210.11715
Autor:
Chen, Meng, Yang, Chenxu, Yu, Minghao, Han, Mengyao, Meng, Zihan, Zhao, Tian, Niu, Jianrui, Mu, Situ, Zhang, Jing, Ma, Junjun, Liu, Chun
Publikováno v:
In Desalination 15 October 2024 587
Autor:
Li, Yunke, Yang, Chenxu, Chen, Meng, Bian, Yonghuan, Niu, Jianrui, Mu, Situ, Zhang, Jing, Liu, Chun, Ma, Junjun
Publikováno v:
In Desalination 12 September 2024 584