ChatGPT as a Negotiator: An Analysis of its Adherence with Proportionality and Equality

This study examines the adherence of ChatGPT (GPT-3.S and GPT-4) to fairness principles, specifically proportionality and equality, in negotiation scenarios. Three distinct negotiation contexts were explored: work-study program funding, company sale proceeds division, and employee bonus allocation. The models were prompted to prioritize proportionality, equality, or no specific fairness principle to assess how they respond in different ethical frameworks. A combination of qualitative and quantitative methods, including dialogue analysis, sentiment tracking, and fairness scoring, was used to evaluate their ne-gotiation behaviors. Results indicate that both models tend to favor proportionality by default, with GPT-4 showing greater adaptability compared to GPT-3.S. When explicitly directed to prioritize equality, the models followed these instructions but maintained a largely assertive negotiation style with limited engagement in dynamic exchanges. Sentiment analysis revealed that both models adopted increasingly positive tones as nego-tiations progressed. However, both versions were susceptible to prompt manipulation, potentially compromising fairness in some outcomes. This research highlights the potential of LLMs like ChatGPT in automating fair negotiations, though improvements in consistency, adaptability, and safeguards against manipulation are necessary for more robust, ethical applications in real-world scenarios.