paper-with-me

홈 › Papers

Activation Matching for Explanation Generation

2025-09-27 · Pirzada Suhail, Aditya Anand, Amit Sethi arxiv

In this paper we introduce an activation-matching--based approach to generate minimal, faithful explanations for the decision-making of a pretrained classifier on any given image. Given an input image $x$ and a frozen model $f$, we train a lightweight autoencoder to output a binary mask $m$ such that the explanation $e = m \odot x$ preserves both the model's prediction and the intermediate activations of \(x\). Our objective combines: (i) multi-layer activation matching with KL divergence to align distributions and cross-entropy to retain the top-1 label for both the image and the explanation; (ii) mask priors -- L1 area for minimality, a binarization penalty for crisp 0/1 masks, and total variation for compactness; and (iii) abductive constraints for faithfulness and necessity. Together, these objectives yield small, human-interpretable masks that retain classifier behavior while discarding irrelevant input regions, providing practical and faithful minimalist explanations for the decision making of the underlying model.

📄 PDF Abstract BibTeX arXiv:2509.23051

Code (0)

등록된 구현이 없습니다.

Tasks

Explanation GenerationDecision Making

Similar Papers 제목 키워드 기반

EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation Matching

2025-09-30 · Pirzada Suhail, Aditya Anand, Amit Sethi arxiv

Machine learning models, by virtue of training, learn a large repertoire of decision rules for any given input, and any one of these may suffice to justify a prediction. However, in high-dimensional input spaces, such ru…

Explanation Generation

Med-CAM: Minimal Evidence for Explaining Medical Decision Making

2026-04-15 · Pirzada Suhail, Aditya Anand, Amit Sethi arxiv

Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black bo…

Decision Making

SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models

2025-11-25 · Jiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du arxiv

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have e…

Learning from Natural Language Explanations for Generalizable Entity Matching

2024-06-13 · Somin Wadhwa, Adit Krishnan, Runhui Wang, Byron C. Wallace 외

Entity matching is the task of linking records from different sources that refer to the same real-world entity. Past work has primarily treated entity linking as a standard supervised learning problem. However, supervise…

Binary ClassificationDomain GeneralizationEntity LinkingEntity Resolution+1

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

2026-05-25 · Haiyan Zhao, Zirui He, Guanchu Wang, Ali Payani 외 arxiv

Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own activations. We introduce Universal Activa…