Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

• URL: http://arxiv.org/abs/2010.11506v1
• Date: Thu, 22 Oct 2020 07:48:38 GMT
• Title: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
• Authors: Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao, Chao Zhang
• Abstract summary: Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution data. We propose a regularized fine-tuning method to mitigate this issue. Our method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets.
• Score: 42.58055728867802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encourages the model to output uniform distributions for pseudo off-manifold samples to address the over-confidence issue for OOD data. Our experiments demonstrate that the proposed method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. Our code can be found at https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning.

Related papers

• Learnable Chernoff Baselines for Inference-Time Alignment [64.81256817158851]
  We introduce Learnable Chernoff Baselines as a method for efficiently and approximately sampling from exponentially tilted kernels.<n>We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling.
  arXiv  Detail & Related papers  (2026-02-08T00:09:40Z)
• CalibrateMix: Guided-Mixup Calibration of Image Semi-Supervised Models [49.588973929678765]
  CalibrateMix is a mixup-based approach that aims to improve the calibration of SSL models.<n>Our method achieves lower expected calibration error (ECE) and superior accuracy compared to existing SSL approaches.
  arXiv  Detail & Related papers  (2025-11-17T04:43:53Z)
• Enhancing Diffusion Model Guidance through Calibration and Regularization [9.22066257345387]
  This paper introduces two complementary contributions to address this issue.<n>First, we propose a differentiable calibration objective based on the Smooth Expected Error (Smooth ECE)<n>Second, we develop enhanced sampling guidance methods that operate on off-the-shelf classifiers without requiring retraining.
  arXiv  Detail & Related papers  (2025-11-08T04:23:42Z)
• Instance-Wise Monotonic Calibration by Constrained Transformation [7.331937231993605]
  A common approach for calibration is fitting a post-hoc calibration map on unseen validation data.<n>Most existing post-hoc calibration methods do not guarantee monotonicity.<n>We propose a family of novel monotonic post-hoc calibration methods.
  arXiv  Detail & Related papers  (2025-07-09T03:32:49Z)
• Beyond One-Hot Labels: Semantic Mixing for Model Calibration [22.39558434131574]
  We introduce calibration-aware data augmentation to create synthetic datasets of diverse samples and their ground-truth uncertainty. We propose calibrated reannotation to tackle the misalignment between the annotated confidence score and the mixing ratio. Experimental results demonstrate that CSM achieves superior calibration compared to the state-of-the-art calibration approaches.
  arXiv  Detail & Related papers  (2025-04-18T08:26:18Z)
• Informed Correctors for Discrete Diffusion Models [32.87362154118195]
  We propose a family of informed correctors that more reliably counteracts discretization error by leveraging information learned by the model. We also propose $k$-Gillespie's, a sampling algorithm that better utilizes each model evaluation, while still enjoying the speed and flexibility of $tau$-leaping. Across several real and synthetic datasets, we show that $k$-Gillespie's with informed correctors reliably produces higher quality samples at lower computational cost.
  arXiv  Detail & Related papers  (2024-07-30T23:29:29Z)
• Calibration-Aware Bayesian Learning [37.82259435084825]
  This paper proposes an integrated framework, referred to as calibration-aware Bayesian neural networks (CA-BNNs) It applies both data-dependent or data-independent regularizers while optimizing over a variational distribution as in Bayesian learning. Numerical results validate the advantages of the proposed approach in terms of expected calibration error (ECE) and reliability diagrams.
  arXiv  Detail & Related papers  (2023-05-12T14:19:15Z)
• On Calibrating Diffusion Probabilistic Models [78.75538484265292]
  diffusion probabilistic models (DPMs) have achieved promising results in diverse generative tasks. We propose a simple way for calibrating an arbitrary pretrained DPM, with which the score matching loss can be reduced and the lower bounds of model likelihood can be increased. Our calibration method is performed only once and the resulting models can be used repeatedly for sampling.
  arXiv  Detail & Related papers  (2023-02-21T14:14:40Z)
• On Calibrating Semantic Segmentation Models: Analyses and An Algorithm [51.85289816613351]
  We study the problem of semantic segmentation calibration. Model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. We propose a simple, unifying, and effective approach, namely selective scaling.
  arXiv  Detail & Related papers  (2022-12-22T22:05:16Z)
• Modular Conformal Calibration [80.33410096908872]
  We introduce a versatile class of algorithms for recalibration in regression. This framework allows one to transform any regression model into a calibrated probabilistic model. We conduct an empirical study of MCC on 17 regression datasets.
  arXiv  Detail & Related papers  (2022-06-23T03:25:23Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• Calibration of Neural Networks using Splines [51.42640515410253]
  Measuring calibration error amounts to comparing two empirical distributions. We introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test. Our method consistently outperforms existing methods on KS error as well as other commonly used calibration measures.
  arXiv  Detail & Related papers  (2020-06-23T07:18:05Z)

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.