Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making

• URL: http://arxiv.org/abs/2602.07008v1
• Date: Fri, 30 Jan 2026 10:29:27 GMT
• Title: Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making
• Authors: Ruoyu Chen, Shangquan Sun, Xiaoqing Guo, Sanyi Zhang, Kangwei Liu, Shiming Liu, Zhangcheng Wang, Qunli Zhang, Hua Zhang, Xiaochun Cao,
• Abstract summary: We propose an attribution-based human prior alignment method.<n>We validate our method on both image classification and click decision tasks in MLLM-based GUI agent models.
• Score: 47.85214982772646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typically provides only class-level labels, allowing models to achieve high accuracy through shortcut correlations rather than the intended evidence. Human priors can help constrain such behavior, but aligning models to these priors remains challenging because learned representations often diverge from human perception. To address this challenge, we propose an attribution-based human prior alignment method. We encode human priors as input regions that the model is expected to rely on (e.g., bounding boxes), and leverage a highly faithful subset-selection-based attribution approach to expose the model's decision evidence during training. When the attribution region deviates substantially from the prior regions, we penalize reliance on off-prior evidence, encouraging the model to shift its attribution toward the intended regions. This is achieved through a training objective that imposes attribution constraints induced by the human prior. We validate our method on both image classification and click decision tasks in MLLM-based GUI agent models. Across conventional classification and autoregressive generation settings, human prior alignment consistently improves task accuracy while also enhancing the model's decision reasonability.

Related papers

• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective [12.160708336715489]
  "Model elasticity" provides a unified way to characterize the regret incurred due to model imputation.<n>We show that under the missing at random (MAR) setting, it is possible to sequentially calibrate the pre-trained model.<n>Our analysis highlights the practical value of having an accurate pre-trained model in sequential decision-making tasks.
  arXiv  Detail & Related papers  (2025-07-10T15:33:27Z)
• Preference Learning for AI Alignment: a Causal Perspective [55.2480439325792]
  We frame this problem in a causal paradigm, providing the rich toolbox of causality to identify persistent challenges.<n>Inheriting from the literature of causal inference, we identify key assumptions necessary for reliable generalisation.<n>We illustrate failure modes of naive reward models and demonstrate how causally-inspired approaches can improve model robustness.
  arXiv  Detail & Related papers  (2025-06-06T10:45:42Z)
• Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation [36.07607318734544]
  We introduce a Synergistic training framework for Foundation and Conventional models (SynFoC)<n>We observe that a conventional model trained from scratch has the ability to correct the high-confidence mispredictions of the foundation model.<n>We demonstrate the superiority of our method across four public multi-domain datasets.
  arXiv  Detail & Related papers  (2025-03-21T10:03:32Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Distributionally Robust Post-hoc Classifiers under Prior Shifts [31.237674771958165]
  We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors. We present an extremely lightweight post-hoc approach that performs scaling adjustments to predictions from a pre-trained model.
  arXiv  Detail & Related papers  (2023-09-16T00:54:57Z)
• Prior-guided Source-free Domain Adaptation for Human Pose Estimation [24.50953879583841]
  Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data. We present Prior-guided Self-training (POST), a pseudo-labeling approach that builds on the popular Mean Teacher framework.
  arXiv  Detail & Related papers  (2023-08-26T20:30:04Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)

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.