# Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints

arXiv: https://arxiv.org/abs/2602.07008 · HTML: https://mlsanity.com/paper/2602.07008/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 52 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.01391/) (2025)
- [From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks](https://mlsanity.com/paper/2406.06579/) (2024)
- [Explain Any Concept: Segment Anything Meets Concept-Based Explanation](https://mlsanity.com/paper/2305.10289/) (2023)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure](https://mlsanity.com/paper/2206.06219/) (2022)
- [Token Activation Map to Visually Explain Multimodal LLMs](https://mlsanity.com/paper/2506.23270/) (2025)

## Built on by (most cited first, 2 of 2)

- [PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution](https://mlsanity.com/paper/2606.18008/) (2026)
- [Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations](https://mlsanity.com/paper/2607.23835/) (2026)

## Abstract (arXiv)

Reliable models should not only predict correctly, but also base their decisions on acceptable evidence. However, conventional supervised learning typically provides only class-level labels, allowing models to achieve high accuracy by exploiting shortcut correlations rather than intended decision evidence. Human priors, such as bounding boxes or target interface elements, can help constrain such behavior, but aligning model evidence with these priors remains challenging because learned decision evidence often diverges from human perception. In this work, we study attribution-prior alignment with subset-selection-based attribution. Motivated by prior deletion and insertion evaluations showing that subset-selection attribution can identify compact decision-supporting regions, we use it as a training-time signal to expose the model's attributed evidence. When the top-attributed evidence deviates substantially from the prior region, we penalize off-prior attribution and encourage the model to shift its attributed evidence toward the intended regions. This yields a selective prior-constrained objective that avoids uniformly suppressing all non-prior regions. We validate our method on both image classification and click decision tasks in MLLM-based GUI agents. Across discriminative classification and autoregressive decision-making settings, our method improves task accuracy while enhancing attribution-prior alignment.