Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks
Yingzhe Peng, Xiaoting Qin, Zhiyang Zhang, Jue Zhang, Qingwei Lin, Xu Yang, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
2024-11-01
Summary
This paper presents CARE, a chat-based system designed to help users explore information more effectively by providing personalized support during complex tasks.
What's the problem?
Many chatbots that use large language models (LLMs) can provide information, but they often struggle to give personalized help, especially when users start with vague questions or don't have enough context. This makes it hard for users to get the specific assistance they need for exploratory tasks.
What's the solution?
The authors introduce the Collaborative Assistant for Personalized Exploration (CARE), which combines a multi-agent LLM framework with a structured user interface. CARE features a Chat Panel for asking questions, a Solution Panel for displaying answers, and a Needs Panel for refining user queries. The system allows multiple agents to work together to understand both what the user explicitly asks and what they might need implicitly, leading to more tailored and actionable solutions. In user studies, participants preferred CARE over traditional chatbots because it reduced their cognitive load and inspired creativity.
Why it matters?
This research is significant because it transforms how LLM-based systems interact with users from being passive information providers to active partners in problem-solving. By enhancing personalization in exploratory tasks, CARE can improve user experiences in various applications, such as research, education, and creative projects.
Abstract
The rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks. However, LLM-based chatbots often struggle to provide personalized support, particularly when users start with vague queries or lack sufficient contextual information. This paper introduces the Collaborative Assistant for Personalized Exploration (CARE), a system designed to enhance personalization in exploratory tasks by combining a multi-agent LLM framework with a structured user interface. CARE's interface consists of a Chat Panel, Solution Panel, and Needs Panel, enabling iterative query refinement and dynamic solution generation. The multi-agent framework collaborates to identify both explicit and implicit user needs, delivering tailored, actionable solutions. In a within-subject user study with 22 participants, CARE was consistently preferred over a baseline LLM chatbot, with users praising its ability to reduce cognitive load, inspire creativity, and provide more tailored solutions. Our findings highlight CARE's potential to transform LLM-based systems from passive information retrievers to proactive partners in personalized problem-solving and exploration.