Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning
This work addresses the challenge of smooth dialogue transitions in sales interactions for improving AI-driven customer service, though it appears incremental as it builds on prior dataset efforts.
This paper tackles the problem of poor naturalness in sales-customer dialogues by introducing SalesBot 2.0, an improved dataset that enhances coherence and reduces aggression, and SalesAgent, a model that excels in transitioning topics and understanding user intents, validated through experiments with diverse user simulations.
Recent research in dialogue systems and corpora has focused on two main categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems help users accomplish specific tasks, while open-domain systems aim to create engaging conversations. However, in real-world scenarios, user intents are often revealed during interactions. A recent study introduced SalesBot, which simulates dialogues transitioning from chit-chat to task-oriented scenarios to train sales agents. Unfortunately, the initial data lacked smooth transitions and coherent long-turn dialogues, resulting in poor naturalness in sales-customer interactions. To address these issues, this paper presents SalesBot 2.0, an improved dataset. It leverages commonsense knowledge from large language models (LLMs) through strategic prompting. Additionally, we introduce a novel model called SalesAgent, trained on salesperson's interactions, using chain-of-thought (CoT) reasoning. This model excels in transitioning topics, understanding user intents, and selecting appropriate strategies. Experiments using diverse user simulations validate the effectiveness of our method in controlling dialogue strategies in LLMs. Furthermore, SalesBot 2.0 enhances coherence and reduces aggression, facilitating better model learning for sales-customer interactions.