Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning

TL;DR

This paper introduces SalesBot 2.0 and SalesAgent, leveraging chain-of-thought reasoning and commonsense knowledge to improve dialogue naturalness, coherence, and strategic control in sales-related large language models.

Contribution

It presents a new dataset and a novel LLM-based model that enhances dialogue transition, intent understanding, and strategy selection in sales conversations.

Findings

SalesBot 2.0 improves dialogue coherence and reduces aggression.

SalesAgent effectively transitions topics and understands user intents.

Experiments show enhanced control over dialogue strategies in LLMs.

Abstract

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.