Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
This work highlights a fundamental challenge for LLM-based agents in simulating real-world social interactions, which is incremental as it builds on existing simulation methods.
The paper tackles the problem of unrealistic social simulations with LLMs by developing an evaluation framework to compare omniscient and non-omniscient settings, finding that LLMs perform better in unrealistic omniscient simulations but struggle in more realistic conditions with information asymmetry.
Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena. However, most recent work has used a more 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 involve humans and AI agents in the real world. To examine these differences, we develop an evaluation framework to simulate social interactions with LLMs in various settings (omniscient, non-omniscient). Our experiments show that LLMs perform better in unrealistic, omniscient simulation settings but struggle in ones that more accurately reflect real-world conditions with information asymmetry. Our findings indicate that addressing information asymmetry remains a fundamental challenge for LLM-based agents.