Imagen de Portada

Towards Verifiable Transformers: Solver-Checkable Circuit Explanations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Somani, Neel
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Logic in Computer Science
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can Transformers Learn to Verify During Backtracking Search?
por: Phua, Yin Jun, et al.
Publicado: (2026)

Lecture Notes on Verifying Graph Neural Networks
por: Schwarzentruber, François
Publicado: (2025)

Space Explanations of Neural Network Classification
por: Labbaf, Faezeh, et al.
Publicado: (2025)

Verifying the Generalization of Deep Learning to Out-of-Distribution Domains
por: Amir, Guy, et al.
Publicado: (2024)

NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis
por: Cosler, Matthias, et al.
Publicado: (2024)

Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimization
por: Filho, Francisco Mateus Rocha, et al.
Publicado: (2026)

Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy
por: Chagas, Vinícius P., et al.
Publicado: (2026)

Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing
por: Queiroz, Luiz Fernando Paulino, et al.
Publicado: (2026)

Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
por: Hadad, Itamar, et al.
Publicado: (2026)

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
por: Alsmann, Eric, et al.
Publicado: (2026)

Verifying Quantized Graph Neural Networks is PSPACE-complete
por: Sälzer, Marco, et al.
Publicado: (2025)

Verifiable Boosted Tree Ensembles
por: Calzavara, Stefano, et al.
Publicado: (2024)

Rigorous Explanations for Tree Ensembles
por: Izza, Yacine, et al.
Publicado: (2026)

On Trustworthy Rule-Based Models and Explanations
por: Siala, Mohamed, et al.
Publicado: (2025)

Formal Explanations for Neuro-Symbolic AI
por: Paul, Sushmita, et al.
Publicado: (2024)

A DPLL(T) Framework for Verifying Deep Neural Networks
por: Duong, Hai, et al.
Publicado: (2023)

A Reinforcement Learning based Reset Policy for CDCL SAT Solvers
por: Li, Chunxiao, et al.
Publicado: (2024)

Boolformer: Symbolic Regression of Logic Functions with Transformers
por: d'Ascoli, Stéphane, et al.
Publicado: (2023)

Scaling the Explanation of Multi-Class Bayesian Network Classifiers
por: Zhang, Yaofang, et al.
Publicado: (2026)

Most General Explanations of Tree Ensembles (Extended Version)
por: Izza, Yacine, et al.
Publicado: (2025)

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
por: Bassan, Shahaf, et al.
Publicado: (2025)

MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
por: Pati, Viresh, et al.
Publicado: (2026)

Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
por: Boetius, David, et al.
Publicado: (2026)

Loop Invariant Generation: A Hybrid Framework of Reasoning optimised LLMs and SMT Solvers
por: Bharti, Varun, et al.
Publicado: (2025)

A Compositional Atlas for Algebraic Circuits
por: Wang, Benjie, et al.
Publicado: (2024)

SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
por: Zhao, Yanxiao, et al.
Publicado: (2025)

Circuit Representations of Random Forests with Applications to XAI
por: Ji, Chunxi, et al.
Publicado: (2026)

CFGs: Causality Constrained Counterfactual Explanations using goal-directed ASP
por: Dasgupta, Sopam, et al.
Publicado: (2024)

How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?
por: Benedikt, Michael, et al.
Publicado: (2026)

Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games
por: Mannucci, Mirco A.
Publicado: (2025)

From learnable objects to learnable random objects
por: Anderson, Aaron, et al.
Publicado: (2025)

Programs as Singularities
por: Murfet, Daniel, et al.
Publicado: (2025)

CoGS: Causality Constrained Counterfactual Explanations using goal-directed ASP
por: Dasgupta, Sopam, et al.
Publicado: (2024)

From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
por: Aljaafari, Nura, et al.
Publicado: (2026)

Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable
por: Chernobrovkin, Artem, et al.
Publicado: (2025)

Formally Verified Neurosymbolic Trajectory Learning via Tensor-based Linear Temporal Logic on Finite Traces
por: Chevallier, Mark, et al.
Publicado: (2025)

Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving
por: Rajaee, Sara, et al.
Publicado: (2025)

Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report
por: Bukhari, Syed Ali Asadullah, et al.
Publicado: (2024)

Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
por: Işık, İlker, et al.
Publicado: (2026)

Lattice Deduction Transformers
por: Davis, Liam, et al.
Publicado: (2026)