Decentralized Aggregation of LLM Predictions via Wagering Mechanisms

• URL: http://arxiv.org/abs/2607.04389v1
• Date: Sun, 05 Jul 2026 16:34:54 GMT
• Title: Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
• Abstract summary: We propose a family of advantage-aligned wagering mechanisms for LLM aggregation.<n>We show that WALLA matches centralized aggregation methods in predictive performance.<n>We also show that WALLA achieves decentralized learning, advantage-aligned aggregation weights, uncertainty awareness, and incentive-compatible prediction.
• Score: 2.670642124118927
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is increasingly common to aggregate predictions from multiple LLMs, each with domain expertise or access to private tools and data, to improve collective prediction performance. In decentralized settings, aggregation weights need to be determined without access to models' private information and should remain robust to strategic reporting. We propose a family of advantage-aligned wagering mechanisms for LLM aggregation (WALLA), in which each model reports a prediction and a learned wager, and predictions are aggregated using wagers as weights. WALLA introduces a leave-one-out baseline into the net payout function, yielding three desirable properties: (1) dominant-strategy incentive compatibility of prediction under arbitrary belief structure, (2) advantage--wager alignment, where the optimal wager is proportional to the model's expected score advantage, and (3) prediction-agnostic wager optimization, enabling decentralized learning of wager policies without requiring optimal predictions. We further instantiate two mechanism variants that trade off normality and no-arbitrage while maintaining a bounded worst-case deficit for the mechanism. Experiments on question-answering and forecasting benchmarks across heterogeneous models and private-information settings show that WALLA matches centralized aggregation methods in predictive performance, while simultaneously achieving decentralized learning, advantage-aligned aggregation weights, uncertainty awareness, and incentive-compatible prediction.

Related papers

• Robust and Consistent Ski Rental with Distributional Advice [13.811651343801579]
  The ski rental problem is a canonical model for online decision-making under uncertainty.<n>We propose a framework that integrates distributional advice of unknown quality into both deterministic and randomized algorithms.<n>We show that our framework improves consistency significantly over existing point-prediction baselines while maintaining comparable robustness.
  arXiv  Detail & Related papers  (2026-03-31T04:04:21Z)
• An Optimised Greedy-Weighted Ensemble Framework for Financial Loan Default Prediction [0.8941624592392746]
  This study proposes an Optimised Greedy-Weighted Ensemble framework for loan default prediction.<n>The proposed framework dynamically allocates model weights based on empirical predictive performance.<n>It provides a scalable data-driven approach to support credit assessment, risk monitoring, and financial decision-making.
  arXiv  Detail & Related papers  (2026-03-19T14:04:37Z)
• Forecasting the U.S. Treasury Yield Curve: A Distributionally Robust Machine Learning Approach [0.12891210250935145]
  We study U.S. Treasury yield curve forecasting under distributional uncertainty.<n>Rather than minimizing average forecast error, the forecaster selects a decision rule that minimizes worst case expected loss.<n>We propose a distributionally robust ensemble forecasting framework that integrates factor models with high dimensional nonparametric machine learning models.
  arXiv  Detail & Related papers  (2026-01-08T05:26:43Z)
• AWPO: Enhancing Tool-Use of Large Language Models through Explicit Integration of Reasoning Rewards [60.2998874976509]
  We propose advantage-weighted policy optimization (AWPO) to integrate explicit reasoning rewards to enhance tool-use capability.<n>AWPO incorporates variance-aware gating and difficulty-aware weighting to adaptively modulate advantages from reasoning signals.<n>Experiments demonstrate that AWPO achieves state-of-the-art performance across standard tool-use benchmarks.
  arXiv  Detail & Related papers  (2025-12-22T08:07:00Z)
• Forests of Uncertaint(r)ees: Using tree-based ensembles to estimate probability distributions of future conflict [0.0]
  We develop a strategy to quantify uncertainty in conflict forecasting, shifting from traditional point predictions to full predictive distributions.<n>Models are able to consistently outperform a suite of benchmarks derived from conflict history in predictions up to one year in advance.<n>We emphasize the need to understand how a metric behaves for a given prediction problem, in our case characterized by extremely high zero-inflatedness.
  arXiv  Detail & Related papers  (2025-12-05T23:10:16Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks [52.46420522934253]
  We introduce LoRA-Ensemble, a parameter-efficient ensembling method for self-attention networks.<n>The method not only outperforms state-of-the-art implicit techniques like BatchEnsemble, but even matches or exceeds the accuracy of an Explicit Ensemble.
  arXiv  Detail & Related papers  (2024-05-23T11:10:32Z)
• 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)
• 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)
• Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
  Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
  arXiv  Detail & Related papers  (2020-12-23T16:21:34Z)

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.