INA: An Integrative Approach for Enhancing Negotiation Strategies with Reward-Based Dialogue Agent
Submission Type: Regular Long Paper
Submission Track: Dialogue and Interactive Systems
Submission Track 2: NLP Applications
Keywords: Negotiation, Dialogue Agent, Prompting
Abstract: In this paper, we propose a novel negotiation agent designed for the online marketplace. Our dialogue agent is integrative in nature i.e, it possesses the capability to negotiate on price as well as other factors, such as the addition or removal of items from a deal bundle, thereby offering a more flexible and comprehensive negotiation experience. To enable this functionality, we create a new dataset called Integrative Negotiation Dataset (IND). For this dataset creation, we introduce a new semi-automated data creation method, which combines defining negotiation intents, actions, and intent-action simulation between users and the agent to generate potential dialogue flows. Finally, the prompting of GPT-J, a state-of-the-art language model, is done to generate dialogues for a given intent, with a human-in-the-loop process for post-editing and refining minor errors to ensure high data quality. We first train a maximum likelihood loss based model on IND, and then employ a set of novel rewards specifically tailored for the negotiation task to train our Integrative Negotiation Agent (INA). These rewards incentivize the agent to learn effective negotiation strategies that can adapt to various contextual requirements and price proposals. We train our model and conduct experiments to evaluate the effectiveness of our reward-based dialogue agent for negotiation. Our results demonstrate that the proposed approach and reward functions significantly enhance the negotiation capabilities of the dialogue agent. The INA successfully engages in integrative negotiations, displaying the ability to dynamically adjust prices and negotiate the inclusion or exclusion of items in a deal bundle.
Submission Number: 5321
Loading