Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs

arXiv:2403.05020v1 Announce Type: new
Abstract: Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena with LLM-based agents. However, most work has used an omniscient perspective on these simulations (e.g., single LLM to generate all interlocutors), which is fundamentally at odds with the non-omniscient, information asymmetric interactions that humans have. To examine these differences, we develop an evaluation framework to simulate social interactions with LLMs in various settings (omniscient, non-omniscient). …

abstract advances agents arxiv cs.ai cs.cl fantasy however interactions language language models large language large language models life llm llms perspective simulations social study success type work