Maximizing the Social Welfare of Decentralized Knowledge Inference Through Evolutionary Game

To broaden their domain knowledge coverage, large language models (LLMs) increasingly incorporate extensive cor-pus data from various industries. These heterogeneous datasets are often maintained by different stakeholders, where issues of data heterogeneity, privacy, and the network cost of data transmission have attracted much attention. To address these challenges, researchers have studied the integration of LLMs with knowledge graphs to manage data heterogeneity and with edge computing to ensure data privacy and transmission efficiency. In this work, we introduce a reputation system and a spot-check mechanism for a decentralized knowledge inference system in which edge nodes can collaborate with others for knowledge sharing while preserving their data privacy. We then use an evolutionary game model to study the dynamic decision-making between requestors and workers. Moreover, we show that higher reward values and higher model quality accelerate the maximization of social welfare.