Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation

2026-04-13

AI Summary

This work addresses the limitation of traditional customer service chatbots, which passively respond to user queries and struggle to proactively acquire high-value business information efficiently. The paper introduces, for the first time, the task of “proactive information probing” and presents PROCHATIP, a novel framework that strategically controls probing timing to collect predefined target information while minimizing user disruption and dialogue turns. Central to PROCHATIP is a dedicated dialogue policy module that enables the agent to autonomously determine when and how to initiate probing actions. Experimental results demonstrate that PROCHATIP significantly outperforms existing baselines in both information acquisition efficiency and service quality, highlighting its potential as a low-cost, scalable engine for proactive business intelligence.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Information Extraction
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Customer service chatbots are increasingly expected to serve not merely as reactive support tools for users, but as strategic interfaces for harvesting high-value information and business intelligence. In response, we make three main contributions. 1) We introduce and define a novel task of Proactive Information Probing, which optimizes when to probe users for pre-specified target information while minimizing conversation turns and user friction. 2) We propose PROCHATIP, a proactive chatbot framework featuring a specialized conversation strategy module trained to master the delicate timing of probes. 3) Experiments demonstrate that PROCHATIP significantly outperforms baselines, exhibiting superior capability in both information probing and service quality. We believe that our work effectively redefines the commercial utility of chatbots, positioning them as scalable, cost-effective engines for proactive business intelligence. Our code is available at https://github.com/SCUNLP/PROCHATIP.

Problem

• Proactive Information Probing
• Customer Service Chatbots
• Business Intelligence
• Conversation Strategy
• User Friction

Innovation

• Proactive Information Probing
• Chatbot Framework
• Conversation Strategy
• Business Intelligence
• User Friction Minimization