KEEP CHATTING! An Attractive Dataset for Continuous Conversation Agents

Yihe Wang, Jin Liu, Yao Wan, Yitong Li, Zifeng Liu, Weipeng Chen


Abstract
Ongoing chatting is an important step for conversational agents to build long-term connections with people. However, people tend to quickly lose interest in chatting if the conversational agent’s words are not engaging enough. In this paper, we present a novel task of increasing users’ willingness to continue talking to the agent.We collect a dataset named ContinuousChat by: (i) collecting personas and revising them, and then expanding the personas to detailed-personas through experiences, daily life, future plans, or interesting stories; (ii) expanding detailed-personas into the dialogues, and inject emotions and feelings into them; (iii) rewriting the dialogues in specific styles through few-shot prompt, conditioning on handwritten style-specific examples.We benchmark LLMs on ContinuousChat Dataset using both fine-tuning and in-context learning settings. Experiments over publicly available models demonstrate that although there is substantial room for improvement in generating style-specific dialogues, our ContinuousChat dataset is valuable in guiding conversational agents to generate more attractive dialogues and increase users’ willingness to continue the conversations.
Anthology ID:
2024.findings-acl.972
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16408–16414
Language:
URL:
https://aclanthology.org/2024.findings-acl.972
DOI:
Bibkey:
Cite (ACL):
Yihe Wang, Jin Liu, Yao Wan, Yitong Li, Zifeng Liu, and Weipeng Chen. 2024. KEEP CHATTING! An Attractive Dataset for Continuous Conversation Agents. In Findings of the Association for Computational Linguistics ACL 2024, pages 16408–16414, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
KEEP CHATTING! An Attractive Dataset for Continuous Conversation Agents (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.972.pdf