{"ID":2823817,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.25063","arxiv_id":"2512.25063","title":"Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity","abstract":"Despite their scale and success, modern transformers are usually trained as single-minded systems: optimization produces a deterministic set of parameters, representing a single functional hypothesis about the data. Motivated by the analogy to human populations, in which population-level intelligence emerges from diverse individual behaviors, we propose Population Bayesian Transformers (B-Trans), which enable sampling diverse yet coherent transformer large language model instances (hereafter referred to as a 'mind') from a single pre-trained LLM. B-Trans introduces a Bayesian-inspired posterior proxy by injecting stochasticity directly into normalization layers, avoiding the prohibitive cost of training full Bayesian neural networks. Sampling from this proxy yields a population of minds with diverse behaviors while maintaining general competence. During the generation of each response, we sample a single realization from the random distribution and hold it fixed, ensuring temporal consistency and reasoning coherence. Experiments on zero-shot generation and Reinforcement Learning with Verifiable Rewards (RLVR) demonstrate that B-Trans effectively leverages the stochastic model diversity, yielding superior response diversity while achieving better task performance compared to deterministic baselines.","short_abstract":"Despite their scale and success, modern transformers are usually trained as single-minded systems: optimization produces a deterministic set of parameters, representing a single functional hypothesis about the data. Motivated by the analogy to human populations, in which population-level intelligence emerges from diver...","url_abs":"https://arxiv.org/abs/2512.25063","url_pdf":"https://arxiv.org/pdf/2512.25063v2","authors":"[\"Diji Yang\",\"Yi Zhang\"]","published":"2025-12-31T18:56:02Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}