GNOME: Generating Negotiations through Open-Domain Mapping of Exchanges
This work addresses the generalizability issue in negotiation systems for AI applications, reducing the need for expensive manual data curation, though it is incremental as it builds on existing methods for data generation.
The paper tackles the problem that language models trained for negotiation in closed domains do not generalize well to open domains, and proposes GNOME, an automated framework that uses large language models to generate synthetic open-domain negotiation dialogues from closed-domain data. The results show that models trained on GNOME-generated data outperform previous state-of-the-art models in domain-specific strategy prediction and generalize better to unseen domains.
Language Models have previously shown strong negotiation capabilities in closed domains where the negotiation strategy prediction scope is constrained to a specific setup. In this paper, we first show that these models are not generalizable beyond their original training domain despite their wide-scale pretraining. Following this, we propose an automated framework called GNOME, which processes existing human-annotated, closed-domain datasets using Large Language Models and produces synthetic open-domain dialogues for negotiation. GNOME improves the generalizability of negotiation systems while reducing the expensive and subjective task of manual data curation. Through our experimental setup, we create a benchmark comparing encoder and decoder models trained on existing datasets against datasets created through GNOME. Our results show that models trained on our dataset not only perform better than previous state of the art models on domain specific strategy prediction, but also generalize better to previously unseen domains.