UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs

• URL: http://arxiv.org/abs/2606.06622v2
• Date: Mon, 08 Jun 2026 22:52:18 GMT
• Title: UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs
• Abstract summary: We introduce UnpredictaBench, an evaluation that tests the ability of large language models to capture true underlying distributions.<n>We find that even simple distributional simulation remains challenging, making it a necessary first step toward using LLMs as stand-ins for complex systems.
• Score: 21.05820098186702
• License: http://creativecommons.org/licenses/by/4.0/
• 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 for this setting: simulation requires samples that are calibrated to a target distribution, not merely varied outputs. UnpredictaBench isolates a simplified but fundamental version of this problem: sampling outcomes from individual target distributions, including canonical statistical distributions, distributions induced by stochastic programs, and natural-language scenarios that describe random processes. We introduce 448 such problems together with KS@N, a general-purpose evaluation metric that quantifies how well a model outputs approximate black-box target distributions via the Kolmogorov-Smirnov statistical test. This is the rate at which we fail to reject model samples of size N against ground-truth samples, with larger N indicating greater difficulty. Tested across open and proprietary models, we find a large spread in distributional capabilities. For instance, when models generate samples of size 100 (KS@100, our standard metric), scores range from near 0 to over 20%. No model is able to achieve over 40% at KS@100, showing significant headroom in distributional sampling as a capability. Although adding reasoning can somewhat increase scores, we find no immediate solution for this issue. UnpredictaBench shows that even simple distributional simulation remains challenging, making it a necessary first step toward using LLMs as stand-ins for complex systems.

Related papers

• The Illusion of Stochasticity in LLMs [21.172079837071724]
  We demonstrate that reliable sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents.<n>We show that while powerful frontier models can convert provided random seeds to target distributions, their ability to sample directly from specific distributions is fundamentally flawed.
  arXiv  Detail & Related papers  (2026-04-08T00:44:14Z)
• Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions [50.1404916337174]
  We present the first large-scale, statistically powered audit of native probabilistic sampling in large language models (LLMs)<n>We show that batch generation achieves only modest statistical validity, with a 13% median pass rate, while independent requests collapse almost entirely.<n>We conclude that current LLMs lack a functional internal sampler, necessitating the use of external tools for applications requiring statistical guarantees.
  arXiv  Detail & Related papers  (2026-01-08T22:33:12Z)
• Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling [59.133428586090226]
  Large language models (LLMs) can often accurately describe probability distributions using natural language.<n>This mismatch limits their use in tasks requiring reliableity, such as Monte Carlo methods, agent-based simulations, and randomized decision-making.<n>We introduce Verbalized Rejection Sampling (VRS), a natural-language adaptation of classical rejection sampling.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• Minimax Optimality of the Probability Flow ODE for Diffusion Models [8.15094483029656]
  This work develops the first end-to-end theoretical framework for deterministic ODE-based samplers.<n>We propose a smooth regularized score estimator that simultaneously controls both the $L2$ score error and the associated mean Jacobian error.<n>We demonstrate that the resulting sampler achieves the minimax rate in total variation distance, modulo logarithmic factors.
  arXiv  Detail & Related papers  (2025-03-12T17:51:29Z)
• Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations [15.379345372327375]
  Large Language Models (LLMs) are increasingly being used to simulate human-like decision making in agent-based financial market models.<n>We test three state-of-the-art GPT models for bias using two model sampling approaches: one-shot and few-shot API queries.
  arXiv  Detail & Related papers  (2025-01-20T10:36:51Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Controllable Generation via Locally Constrained Resampling [77.48624621592523]
  We propose a tractable probabilistic approach that performs Bayesian conditioning to draw samples subject to a constraint. Our approach considers the entire sequence, leading to a more globally optimal constrained generation than current greedy methods. We show that our approach is able to steer the model's outputs away from toxic generations, outperforming similar approaches to detoxification.
  arXiv  Detail & Related papers  (2024-10-17T00:49:53Z)
• Efficient Propagation of Uncertainty via Reordering Monte Carlo Samples [0.7087237546722617]
  Uncertainty propagation is a technique to determine model output uncertainties based on the uncertainty in its input variables. In this work, we investigate the hypothesis that while all samples are useful on average, some samples must be more useful than others. We introduce a methodology to adaptively reorder MC samples and show how it results in reduction of computational expense of UP processes.
  arXiv  Detail & Related papers  (2023-02-09T21:28:15Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.