Many Minds from One Model: Bayesian Transformers for Population Intelligence

• URL: http://arxiv.org/abs/2512.25063v1
• Date: Wed, 31 Dec 2025 18:56:02 GMT
• Title: Many Minds from One Model: Bayesian Transformers for Population Intelligence
• Authors: Diji Yang, Yi Zhang,
• Abstract summary: We propose Population Bayesian Transformers (B-Trans) to transform a standard Large Language Model into a Bayesian Transformer model.<n>B-Trans supports sampling diverse yet coherent model instances from a single set of pre-trained weights.<n> Experiments show that B-Trans effectively leverage the wisdom of crowds, yielding superior semantic diversity while achieving better task performance.
• Score: 6.675008419230873
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their scale and success, modern transformers are almost universally trained as single-minded systems: optimization produces one deterministic set of parameters, representing a single functional hypothesis about the data. Motivated by the idea that intelligence emerge from many minds, we propose Population Bayesian Transformers (B-Trans), which transform a standard Large Language Model into a Bayesian Transformer model to supports sampling diverse yet coherent model instances from a single set of pre-trained weights. B-Trans introduces a Bayesian-motivated posterior proxy by treating the bias-like offsets in normalization layers as stochastic variables with a Gaussian variational approximation, inducing a distribution over model behavior without the cost of training full Bayesian neural networks. Sampling from this proxy yields a set of model instances with diverse behaviors while maintaining general competence. To preserve coherence within each generation, we freeze the sampled noise at the sequence level, enforcing temporal consistency across tokens. B-Trans allows for population-level decision-making, where aggregating predictions across sampled individuals significantly enhances exploration. Experiments across zero-shot generation, Reinforcement Learning with Verifiable Rewards (RLVR), and RL without explicit labels demonstrate that B-Trans effectively leverage the wisdom of crowds, yielding superior semantic diversity while achieving better task performance compared to deterministic baselines.

Related papers

• Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts [33.677249894085186]
  We explore the potential of Concept Bottleneck Models for transforming complex, non-interpretable foundation models into interpretable decision-making pipelines.<n>Specifically, we focus on the test-time deployment of such an interpretable CBM pipeline "in the wild"<n>Our adaptation method produces concept-based interpretations better aligned with the test data and boosts post-deployment accuracy by up to 28%.
  arXiv  Detail & Related papers  (2024-12-18T17:47:46Z)
• Measuring training variability from stochastic optimization using robust nonparametric testing [5.519968037738177]
  We propose a robust hypothesis testing framework and a novel summary statistic, the $alpha$-trimming level, to measure model similarity.<n>Applying hypothesis testing directly with the $alpha$-trimming level is challenging because we cannot accurately describe the distribution under the null hypothesis.<n>We show how to use the $alpha$-trimming level to measure model variability and demonstrate experimentally that it is more expressive than performance metrics.
  arXiv  Detail & Related papers  (2024-06-12T15:08:15Z)
• Improving Out-of-Distribution Robustness of Classifiers via Generative Interpolation [56.620403243640396]
  Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly when handling out-of-distribution (OoD) data. We develop a simple yet effective method called Generative Interpolation to fuse generative models trained from multiple domains for synthesizing diverse OoD samples.
  arXiv  Detail & Related papers  (2023-07-23T03:53:53Z)
• Neural Spline Search for Quantile Probabilistic Modeling [35.914279831992964]
  We propose a non-parametric and data-driven approach, Neural Spline Search (NSS), to represent the observed data distribution without parametric assumptions. We demonstrate that NSS outperforms previous methods on synthetic, real-world regression and time-series forecasting tasks.
  arXiv  Detail & Related papers  (2023-01-12T07:45:28Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space [34.83587750498361]
  Diverse human motion prediction aims at predicting multiple possible future pose sequences from a sequence of observed poses. Previous approaches usually employ deep generative networks to model the conditional distribution of data, and then randomly sample outcomes from the distribution. We propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution.
  arXiv  Detail & Related papers  (2022-07-15T09:03:57Z)
• SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities [76.97949110580703]
  We introduce SUPERB-SG, a new benchmark to evaluate pre-trained models across various speech tasks. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.
  arXiv  Detail & Related papers  (2022-03-14T04:26:40Z)
• Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation [3.9318191265352196]
  We propose a semisupervised discrete latent variable model for multi-class text classification and text generation. The proposed model employs the concept of transfer learning for training a quantized transformer model. Experimental results indicate that the proposed model has surpassed the state-of-the-art models remarkably.
  arXiv  Detail & Related papers  (2021-11-10T07:07:54Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)
• Relaxed-Responsibility Hierarchical Discrete VAEs [3.976291254896486]
  We introduce textitRelaxed-Responsibility Vector-Quantisation, a novel way to parameterise discrete latent variables. We achieve state-of-the-art bits-per-dim results for various standard datasets.
  arXiv  Detail & Related papers  (2020-07-14T19:10:05Z)
• Variational Transformers for Diverse Response Generation [71.53159402053392]
  Variational Transformer (VT) is a variational self-attentive feed-forward sequence model. VT combines the parallelizability and global receptive field computation of the Transformer with the variational nature of the CVAE. We explore two types of VT: 1) modeling the discourse-level diversity with a global latent variable; and 2) augmenting the Transformer decoder with a sequence of finegrained latent variables.
  arXiv  Detail & Related papers  (2020-03-28T07:48:02Z)

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.