Toward Ethical AI Through Bayesian Uncertainty in Neural Question Answering

• URL: http://arxiv.org/abs/2512.17677v1
• Date: Fri, 19 Dec 2025 15:17:19 GMT
• Title: Toward Ethical AI Through Bayesian Uncertainty in Neural Question Answering
• Authors: Riccardo Di Sipio,
• Abstract summary: We show how posterior inference conveys confidence in predictions.<n>We then extend this to language models, applying Bayesian inference first to a frozen head and finally to LoRA-adapted transformers.<n>An I don't know'' response not only improves interpretability but also illustrates how Bayesian methods can contribute to more responsible and ethical deployment of neural question-answering systems.
• Score: 0.4873362301533824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We explore Bayesian reasoning as a means to quantify uncertainty in neural networks for question answering. Starting with a multilayer perceptron on the Iris dataset, we show how posterior inference conveys confidence in predictions. We then extend this to language models, applying Bayesian inference first to a frozen head and finally to LoRA-adapted transformers, evaluated on the CommonsenseQA benchmark. Rather than aiming for state-of-the-art accuracy, we compare Laplace approximations against maximum a posteriori (MAP) estimates to highlight uncertainty calibration and selective prediction. This allows models to abstain when confidence is low. An ``I don't know'' response not only improves interpretability but also illustrates how Bayesian methods can contribute to more responsible and ethical deployment of neural question-answering systems.

Related papers

• Tractable Function-Space Variational Inference in Bayesian Neural Networks [72.97620734290139]
  A popular approach for estimating the predictive uncertainty of neural networks is to define a prior distribution over the network parameters. We propose a scalable function-space variational inference method that allows incorporating prior information. We show that the proposed method leads to state-of-the-art uncertainty estimation and predictive performance on a range of prediction tasks.
  arXiv  Detail & Related papers  (2023-12-28T18:33:26Z)
• Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability [50.44439018155837]
  We propose to include a calibration term directly into the training objective of the neural model. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
  arXiv  Detail & Related papers  (2023-10-20T10:20:45Z)
• Do Bayesian Variational Autoencoders Know What They Don't Know? [0.6091702876917279]
  The problem of detecting the Out-of-Distribution (OoD) inputs is paramount importance for Deep Neural Networks. It has been previously shown that even Deep Generative Models that allow estimating the density of the inputs may not be reliable. This paper investigates three approaches to inference: Markov chain Monte Carlo, Bayes gradient by Backpropagation and Weight Averaging-Gaussian.
  arXiv  Detail & Related papers  (2022-12-29T11:48:01Z)
• Uncertainty of Feed Forward Neural Networks Recognizing Quantum Contextuality [2.5665227681407243]
  A powerful technique for estimating both the accuracy and the uncertainty is provided by Bayesian neural networks (BNNs) We show how BNNs can highlight their ability of reliable uncertainty estimation even after training with biased data sets.
  arXiv  Detail & Related papers  (2022-12-27T17:33:46Z)
• Understanding Approximation for Bayesian Inference in Neural Networks [7.081604594416339]
  I explore approximate inference in Bayesian neural networks. The expected utility of the approximate posterior can measure inference quality. Continual and active learning set-ups pose challenges that have nothing to do with posterior quality.
  arXiv  Detail & Related papers  (2022-11-11T11:31:13Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Bayesian Neural Networks for Reversible Steganography [0.7614628596146599]
  We propose to consider uncertainty in predictive models based upon a theoretical framework of Bayesian deep learning. We approximate the posterior predictive distribution through Monte Carlo sampling with reversible forward passes. We show that predictive uncertainty can be disentangled into aleatoric uncertainties and these quantities can be learnt in an unsupervised manner.
  arXiv  Detail & Related papers  (2022-01-07T14:56:33Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks [65.24701908364383]
  We show that a sufficient condition for a uncertainty on a ReLU network is "to be a bit Bayesian calibrated" We further validate these findings empirically via various standard experiments using common deep ReLU networks and Laplace approximations.
  arXiv  Detail & Related papers  (2020-02-24T08:52:06Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)

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.