Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues
Authors
Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special goals. Creating a unified conversational model that can engage in both chit-chat and task-oriented dialogue is a promising research topic in recent years. However, the potential ``initiative'' that occurs when there is a change between dialogue modes in one dialogue has rarely been explored. In this work, we investigate two kinds of dialogue scenarios, one starts from chit-chat implicitly involving task-related topics and finally switching to task-oriented requests; the other starts from task-oriented interaction and eventually changes to casual chat after all requested information is provided. We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model. One is a discrete prompt model trained with two discrete tokens, the other one is a continuous prompt model using continuous prompt embeddings automatically generated by a classifier. We furthermore show that the continuous prompt model can also be used to guide the proactive transitions between particular domains in a multi-domain task-oriented setting.
Research Questions / Practical Problems
Question signals indexed for this paper.
Research Questions
3- How can conversational systems achieve bidirectional proactive switching between chit-chat and task-oriented dialogue modes?Category: Dialogue System Management and Error HandlingSimilar questionsarrow_forward
- Which methods can improve conversational systems' ability to switch modes multiple times in complex scenarios?Category: Dialogue System Management and Error HandlingSimilar questionsarrow_forward
- How can discrete and continuous prompt learning frameworks improve the accuracy of generative mode switching?Category: Dialogue System Management and Error HandlingSimilar questionsarrow_forward
Practical Problems
1- Existing conversational systems cannot naturally switch between chat and task-processing modes, degrading user experience.Category: Dialogue System Management and Error HandlingSimilar questionsarrow_forward
- 75%
General Practitioners’ Perspectives on a Pre-Consultation Chatbot for Shared Decision-Making
DIS '25· Conversational Chatbots +2
- 67%
Rethinking Interaction: From Instrumental Interaction to Human-Computer Partnerships
CHI '18· Human-LLM Collaboration +1
- 67%
To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models
CHI '25· Human-LLM Collaboration +1
- 67%
Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant
CHI '25· Human-LLM Collaboration +1
- 67%
Chatbots as Advisers: the Effects of Response Variability and Reply Suggestion Buttons
CUI '23· Conversational Chatbots +1
- 67%
The User Experience of ChatGPT: Findings From a Questionnaire Study of Early Users
CUI '23· Conversational Chatbots +1
- 67%
Automating the Development of Task-oriented LLM-based Chatbots
CUI '24· Conversational Chatbots +1
- 67%
Towards an optimal dialog strategy for information retrieval using both open-ended and close-ended questions
IUI '18· Conversational Chatbots +1
- 67%
Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate
IUI '24· Human-LLM Collaboration +1
- 67%
C-PAK: Correcting and Completing Variable-length Prefix-based Abbreviated Keystrokes
UIST '23· Human-LLM Collaboration +1
Based on Jaccard similarity of research subtopics & professions (≥60%)