How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation
This addresses the need for systematic evaluation of LLM believability in human behavior simulation, which is incremental as it provides a new benchmark for a known bottleneck in AI assessment.
The authors tackled the problem of evaluating how believably large language models (LLMs) simulate human behaviors by designing SimulateBench, a benchmark with 65 character profiles and 8,400 questions, and found that current LLMs struggle to align with characters and are vulnerable to perturbations.
In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors, the believability of LLMs among humans remains ambiguous, i.e., it is unclear which behaviors of LLMs are convincingly human-like and which need further improvements. In this work, we design SimulateBench to evaluate the believability of LLMs when simulating human behaviors. In specific, we evaluate the believability of LLMs based on two critical dimensions: 1) consistency: the extent to which LLMs can behave consistently with the given information of a human to simulate; and 2) robustness: the ability of LLMs' simulated behaviors to remain robust when faced with perturbations. SimulateBench includes 65 character profiles and a total of 8,400 questions to examine LLMs' simulated behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters. The experimental results reveal that current LLMs struggle to align their behaviors with assigned characters and are vulnerable to perturbations in certain factors.