Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917794715533312 |
|---|---|
| author | Mao, Manqing Ting, Paishun Xiang, Yijian Xu, Mingyang Chen, Julia Lin, Jianzhe |
| author_facet | Mao, Manqing Ting, Paishun Xiang, Yijian Xu, Mingyang Chen, Julia Lin, Jianzhe |
| contents | Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights the complexity of multi-user chatbots, introducing the 3W design dimensions: "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), an LLM-based framework tailored for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Conversational Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and appropriate addressees. This paper further proposes an LLM-based Multi-User Simulator (MUS) to ease MUCA's optimization, enabling faster simulation of conversations between the chatbot and simulated users, and speeding up MUCA's early development. In goal-oriented conversations with a small to medium number of participants, MUCA demonstrates effectiveness in tasks like chiming in at appropriate timings, generating relevant content, and improving user engagement, as shown by case studies and user studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04883 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations Mao, Manqing Ting, Paishun Xiang, Yijian Xu, Mingyang Chen, Julia Lin, Jianzhe Computation and Language Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights the complexity of multi-user chatbots, introducing the 3W design dimensions: "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), an LLM-based framework tailored for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Conversational Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and appropriate addressees. This paper further proposes an LLM-based Multi-User Simulator (MUS) to ease MUCA's optimization, enabling faster simulation of conversations between the chatbot and simulated users, and speeding up MUCA's early development. In goal-oriented conversations with a small to medium number of participants, MUCA demonstrates effectiveness in tasks like chiming in at appropriate timings, generating relevant content, and improving user engagement, as shown by case studies and user studies. |
| title | Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.04883 |