Soft Specialists: $α$-Rényi Ensembles for Uncertainty-Aware LLM Post-Training

• URL: http://arxiv.org/abs/2605.27747v1
• Date: Tue, 26 May 2026 22:44:58 GMT
• Title: Soft Specialists: $α$-Rényi Ensembles for Uncertainty-Aware LLM Post-Training
• Abstract summary: Existing training approaches for large language models learn a single set of parameters, based on large volumes of data.<n>We propose an $$-Rényi variational framework for learning distributions over post-training parameters.<n>We identify local stability criteria, demonstrating how model misspecification can make non-degenerate posterior spread locally favourable.
• Score: 4.297453240868895
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogeneous, conflicting and often outright contradictory. As a result, the model is forced to compress conflicting goals, and inherent uncertainties into a single, averaged pattern of behaviour. We propose an $α$-Rényi variational framework for learning distributions over post-training parameters, offering an uncertainty-aware alternative to deep ensemble approaches. The resulting variational objective interpolates between classical variational Bayes and predictively oriented posterior learning, balancing between globally plausible individual models against systems of complementary specialists. We identify local stability criteria, demonstrating how model misspecification can make non-degenerate posterior spread locally favourable, manifesting contradictory or conflicting data as epistemic uncertainty. We apply our framework to LLM post-training, learning an ensemble of LoRA adapters attached to a shared, frozen base model, providing a scalable training procedure for both supervised fine-tuning and preference optimisation. Our approach enables training examples to be softly routed across ensemble members, promoting model specialisation and providing actionable uncertainty estimates across different tasks.

Related papers

• Multi-Objective Reference-Aligned Machine Unlearning [0.6299766708197883]
  Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility.<n>Existing single-objective approaches, such as ascent or random relabeling, often induce forgetting due to conflicting optimization dynamics and unbounded forgetting objectives.<n>We propose a multi-objective framework that jointly optimize forgetting and retention by replacing loss with a bounded KL alignment of predictions on forgotten samples.
  arXiv  Detail & Related papers  (2026-05-29T22:32:40Z)
• Joint Model and Data Sparsification via the Marginal Likelihood [53.29070892356214]
  We propose jointly learning individual feature and sample relevancies, enabling simultaneous model and data sparsification.<n>This symmetric pruning of model and data offers a natural extension that preserves conjugacy.<n> Empirical results across diverse regression tasks affirm that a joint ARD approach consistently yields both sparse and robust prediction models.
  arXiv  Detail & Related papers  (2026-05-28T13:26:53Z)
• Optimal Transport for LLM Reward Modeling from Noisy Preference [21.518348751984433]
  We propose SelectiveRM, a framework grounded in optimal transport.<n>We first devise a Joint Consistency Discrepancy to align the distribution of model predictions with preference data.<n>We then incorporate a Mass Relaxation mechanism via partial transport.<n>This enables the autonomous exclusion of samples with noisy preference that contradict semantic consistency.
  arXiv  Detail & Related papers  (2026-05-07T11:26:04Z)
• Improving Group Robustness on Spurious Correlation via Evidential Alignment [26.544938760265136]
  Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets.<n>Existing methods typically mitigate this issue by using external group annotations or auxiliary deterministic models.<n>We propose Evidential Alignment, a novel framework that leverages uncertainty quantification to understand the behavior of the biased models.
  arXiv  Detail & Related papers  (2025-06-12T22:47:21Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Regularized Neural Ensemblers [55.15643209328513]
  In this study, we explore employing regularized neural networks as ensemble methods.<n>Motivated by the risk of learning low-diversity ensembles, we propose regularizing the ensembling model by randomly dropping base model predictions.<n>We demonstrate this approach provides lower bounds for the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-10-06T15:25:39Z)
• Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Models [0.9940108090221528]
  Aggregation strategies have been developed to pool or fuse the weights and biases of distributed deterministic models. We show that simple application of the aggregation methods associated with FL schemes for deterministic models is either impossible or results in sub-optimal performance.
  arXiv  Detail & Related papers  (2024-03-22T15:02:24Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Posterior Differential Regularization with f-divergence for Improving Model Robustness [95.05725916287376]
  We focus on methods that regularize the model posterior difference between clean and noisy inputs. We generalize the posterior differential regularization to the family of $f$-divergences. Our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness.
  arXiv  Detail & Related papers  (2020-10-23T19:58:01Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)

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.