Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Hua, Yuncheng"'
Recent studies have explored the use of Large Language Models (LLMs) with Retrieval Augmented Generation (RAG) for Knowledge Graph Question Answering (KGQA). They typically require rewriting retrieved subgraphs into natural language formats comprehen
Externí odkaz:
http://arxiv.org/abs/2409.19753
Autor:
Hua, Yuncheng, Huang, Yujin, Huang, Shuo, Feng, Tao, Qu, Lizhen, Bain, Chris, Bassed, Richard, Haffari, Gholamreza
This paper tackles the task of emotion-cause pair extraction in the unsupervised domain adaptation setting. The problem is challenging as the distributions of the events causing emotions in target domains are dramatically different than those in sour
Externí odkaz:
http://arxiv.org/abs/2406.15490
Recent studies have shown that maintaining a consistent response style by human experts and enhancing data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of trai
Externí odkaz:
http://arxiv.org/abs/2406.10882
Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain generalization, where a model is trained on one source domain and tested o
Externí odkaz:
http://arxiv.org/abs/2404.13504
As the parameter scale of large language models (LLMs) grows, jointly training knowledge graph (KG) embeddings with model parameters to enhance LLM capabilities becomes increasingly costly. Consequently, the community has shown interest in developing
Externí odkaz:
http://arxiv.org/abs/2402.11541
Autor:
Zhan, Haolan, Li, Zhuang, Kang, Xiaoxi, Feng, Tao, Hua, Yuncheng, Qu, Lizhen, Ying, Yi, Chandra, Mei Rianto, Rosalin, Kelly, Jureynolds, Jureynolds, Sharma, Suraj, Qu, Shilin, Luo, Linhao, Soon, Lay-Ki, Azad, Zhaleh Semnani, Zukerman, Ingrid, Haffari, Gholamreza
Norm violations occur when individuals fail to conform to culturally accepted behaviors, which may lead to potential conflicts. Remediating norm violations requires social awareness and cultural sensitivity of the nuances at play. To equip interactiv
Externí odkaz:
http://arxiv.org/abs/2402.11178
Autor:
Zhan, Haolan, Wang, Yufei, Feng, Tao, Hua, Yuncheng, Sharma, Suraj, Li, Zhuang, Qu, Lizhen, Azad, Zhaleh Semnani, Zukerman, Ingrid, Haffari, Gholamreza
Negotiation is a crucial ability in human communication. Recently, there has been a resurgent research interest in negotiation dialogue systems, whose goal is to create intelligent agents that can assist people in resolving conflicts or reaching agre
Externí odkaz:
http://arxiv.org/abs/2402.01097
We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations. Specifically, we simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator a
Externí odkaz:
http://arxiv.org/abs/2402.01737
Autor:
Hua, Yuncheng, Li, Zhuang, Luo, Linhao, Satriadi, Kadek Ananta, Feng, Tao, Zhan, Haolan, Qu, Lizhen, Sharma, Suraj, Zukerman, Ingrid, Semnani-Azad, Zhaleh, Haffari, Gholamreza
In today's globalized world, bridging the cultural divide is more critical than ever for forging meaningful connections. The Socially-Aware Dialogue Assistant System (SADAS) is our answer to this global challenge, and it's designed to ensure that con
Externí odkaz:
http://arxiv.org/abs/2402.01736
Autor:
Zhan, Haolan, Li, Zhuang, Wang, Yufei, Luo, Linhao, Feng, Tao, Kang, Xiaoxi, Hua, Yuncheng, Qu, Lizhen, Soon, Lay-Ki, Sharma, Suraj, Zukerman, Ingrid, Semnani-Azad, Zhaleh, Haffari, Gholamreza
Dialogue systems have been widely applied in many scenarios and are now more powerful and ubiquitous than ever before. With large neural models and massive available data, current dialogue systems have access to more knowledge than any people in thei
Externí odkaz:
http://arxiv.org/abs/2304.12026