What Limits LLM-based Human Simulation: LLMs or Our Design?
This addresses the problem of improving human simulation accuracy for researchers, but it is incremental as it builds on existing analysis without presenting new experimental results.
The paper tackles the problem of limitations in LLM-based human simulation, identifying gaps between simulations and real-world observations, and proposes solutions for both LLM limitations and design challenges.
We argue that advancing LLM-based human simulation requires addressing both LLM's inherent limitations and simulation framework design challenges. Recent studies have revealed significant gaps between LLM-based human simulations and real-world observations, highlighting these dual challenges. To address these gaps, we present a comprehensive analysis of LLM limitations and our design issues, proposing targeted solutions for both aspects. Furthermore, we explore future directions that address both challenges simultaneously, particularly in data collection, LLM generation, and evaluation. To support further research in this field, we provide a curated collection of LLM-based human simulation resources.\footnote{https://github.com/Persdre/llm-human-simulation}