UnpredictaBench

UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs

arXiv:2606.06622v1 Announce Type: new Abstract: We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substitutes for other entities (e.g., for humans in economic simulations), the tendency of many models to collapse towards a single plausible answer means a failure to capture the unpredictability of real systems. Recent work on improving output diversity is insufficient...