Total: 1
With the emergence of Large Language Models (LLMs), we now have unprecedented opportunities to incorporate human-like communication and context-aware interactions into artificial systems. But what is the current state of LLMs’ capability of social interaction? Can they truly understand social scenarios, perform social reasoning, or interact with humans as socially competent agents? We propose this tutorial as an introduction to and an overview of different aspects of artificial social intelligence and their relationship with LLMs. In this tutorial, we will explore these questions by introducing scientific methods for evaluating social intelligence in LLMs, highlighting the key challenges, and identifying promising research directions. Participants will not only gain a comprehensive overview of the field’s progress, but also acquire technical skills on analysing and developing LLM-based social intelligence.