Diversity is the Strength of the AI Crowd

• URL: http://arxiv.org/abs/2606.29661v1
• Date: Mon, 29 Jun 2026 00:09:49 GMT
• Title: Diversity is the Strength of the AI Crowd
• Abstract summary: Given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy?<n>We find that individual accuracy is not enough: many frontier LLMs make highly correlated predictions, limiting the value of additional forecasts from the same or similar models.<n>The strongest ensembles combine accurate but diverse forecasters, with models such as modelGrok 4 contributing disproportionately because their predictions are less correlated with other frontier LLMs.
• Score: 4.101606888483043
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy? On binary questions from the Metaculus AI Benchmark, we find that individual accuracy is not enough: many frontier LLMs make highly correlated predictions, limiting the value of additional forecasts from the same or similar models. Instead, the strongest ensembles combine accurate but diverse forecasters, with models such as \model{Grok 4} contributing disproportionately because their predictions are less correlated with other frontier LLMs. These results suggest that the strength of the AI crowd comes not from sampling more forecasts indiscriminately, but from combining forecasts across models with complementary errors, motivating forecasting systems that explicitly optimize for both model quality and diversity.

Related papers

• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis [1.5751034894694789]
  We develop a surrogate-based explanation methodology that bridges the accuracy-interpretability gap.<n>We integrate spectral predictability analysis to quantify each series' inherent forecastability.<n>The resulting framework delivers interpretable, instance-level explanations for state-of-the-art ensemble forecasts.
  arXiv  Detail & Related papers  (2025-10-09T18:49:45Z)
• Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification [9.397157329808254]
  MUSE is a simple information-theoretic method to identify and aggregate well-calibrated subsets of large language models.<n> Experiments on binary prediction tasks demonstrate improved calibration and predictive performance compared to single-model and na"ive ensemble baselines.
  arXiv  Detail & Related papers  (2025-07-09T19:13:25Z)
• Quantile Regression with Large Language Models for Price Prediction [15.277244542405345]
  Large Language Models (LLMs) have shown promise in structured prediction tasks, including regression.<n>We propose a novel quantile regression approach that enables LLMs to produce full predictive distributions.<n>A Mistral-7B model fine-tuned with quantile heads significantly outperforms traditional approaches for both point and distributional estimations.
  arXiv  Detail & Related papers  (2025-06-07T04:19:28Z)
• Can Language Models Use Forecasting Strategies? [14.332379032371612]
  We describe experiments using a novel dataset of real world events and associated human predictions. We find that models still struggle to make accurate predictions about the future.
  arXiv  Detail & Related papers  (2024-06-06T19:01:42Z)
• Predictive Churn with the Set of Good Models [61.00058053669447]
  This paper explores connections between two seemingly unrelated concepts of predictive inconsistency.<n>The first, known as predictive multiplicity, occurs when models that perform similarly produce conflicting predictions for individual samples.<n>The second concept, predictive churn, examines the differences in individual predictions before and after model updates.
  arXiv  Detail & Related papers  (2024-02-12T16:15:25Z)
• Optimizing accuracy and diversity: a multi-task approach to forecast combinations [0.0]
  We present a multi-task optimization paradigm that focuses on solving both problems simultaneously. It incorporates an additional learning and optimization task into the standard feature-based forecasting approach. The proposed approach elicits the essential role of diversity in feature-based forecasting.
  arXiv  Detail & Related papers  (2023-10-31T15:26:33Z)
• Beyond S-curves: Recurrent Neural Networks for Technology Forecasting [60.82125150951035]
  We develop an autencoder approach that employs recent advances in machine learning and time series forecasting. S-curves forecasts largely exhibit a mean average percentage error (MAPE) comparable to a simple ARIMA baseline. Our autoencoder approach improves the MAPE by 13.5% on average over the second-best result.
  arXiv  Detail & Related papers  (2022-11-28T14:16:22Z)
• Restricted Bernoulli Matrix Factorization: Balancing the trade-off between prediction accuracy and coverage in classification based collaborative filtering [45.335821132209766]
  We propose Restricted Bernoulli Matrix Factorization (ResBeMF) to enhance the performance of classification-based collaborative filtering. The proposed model provides a good balance in terms of the quality measures used compared to other recommendation models.
  arXiv  Detail & Related papers  (2022-10-05T13:48:19Z)
• Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting [61.02295959343446]
  This work first proposes a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from interaction modules.<n>We build a general CU-aware regression framework with an original permutation-equivariant uncertainty estimator to do both tasks of regression and uncertainty estimation.<n>We apply the proposed framework to current SOTA multi-agent trajectory forecasting systems as a plugin module.
  arXiv  Detail & Related papers  (2022-07-11T21:17:41Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)
• Feature-weighted Stacking for Nonseasonal Time Series Forecasts: A Case Study of the COVID-19 Epidemic Curves [0.0]
  We investigate ensembling techniques in forecasting and examine their potential for use in nonseasonal time-series. We propose using late data fusion, using a stacked ensemble of two forecasting models and two meta-features that prove their predictive power during a preliminary forecasting stage.
  arXiv  Detail & Related papers  (2021-08-19T14:44:46Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• A framework for probabilistic weather forecast post-processing across models and lead times using machine learning [3.1542695050861544]
  We show how to bridge the gap between sets of separate forecasts from NWP models and the 'ideal' forecast for decision support. We use Quantile Regression Forests to learn the error profile of each numerical model, and use these to apply empirically-derived probability distributions to forecasts. Second, we combine these probabilistic forecasts using quantile averaging. Third, we interpolate between the aggregate quantiles in order to generate a full predictive distribution.
  arXiv  Detail & Related papers  (2020-05-06T16:46:02Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)

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.