paper-with-me

홈 › Papers

FAME: Formal Abstract Minimal Explanation for Neural Networks

2026-03-11 · Ryma Boumazouza, Raya Elsaleh, Melanie Ducoffe, Shahaf Bassan, Guy Katz arxiv

We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural networks while reducing explanation size. Our main contribution is the design of dedicated perturbation domains that eliminate the need for traversal order. FAME progressively shrinks these domains and leverages LiRPA-based bounds to discard irrelevant features, ultimately converging to a formal abstract minimal explanation. To assess explanation quality, we introduce a procedure that measures the worst-case distance between an abstract minimal explanation and a true minimal explanation. This procedure combines adversarial attacks with an optional VERIX+ refinement step. We benchmark FAME against VERIX+ and demonstrate consistent gains in both explanation size and runtime on medium- to large-scale neural networks.

📄 PDF Abstract BibTeX arXiv:2603.10661

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes

2024-05-20 · Dawid Wiśniewski, Zofia Rostek, Artur Nowakowski

People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-genera…

Machine TranslationSentenceTranslation

Contrastive Explanations for Argumentation-Based Conclusions

2021-07-07 · AnneMarie Borg, Floris Bex

In this paper we discuss contrastive explanations for formal argumentation - the question why a certain argument (the fact) can be accepted, whilst another argument (the foil) cannot be accepted under various extension-b…

A Formal Framework for the Explanation of Finite Automata Decisions

2026-02-12 · Jaime Cuartas Granada, Alexey Ignatiev, Peter J. Stuckey arxiv

Finite automata (FA) are a fundamental computational abstraction that is widely used in practice for various tasks in computer science, linguistics, biology, electrical engineering, and artificial intelligence. Given an …

Taming Silent Failures: A Framework for Verifiable AI Reliability

2025-10-25 · Guan-Yan Yang, Farn Wang arxiv

The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper int…

Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations

2018-02-19 · Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users. One aspect of the explanation generation problem that has yet to receive much atte…

Explanation Generation