interpretability

Documents about interpretability

• Mechanistic Interpretability Needs a Logic of Inference#680162PsyArXiv
• Interpretability, decision trees, sequential decision making#156030HAL (France)
• Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models#131327arXiv (OAI)
• Algorithmic Grammar of Flexible Cognition: A Walk through Latent Operations#428554OSF
• Interpretability and Unification#93210PhilArchive
• Radical AI Interpretability#691163PhilArchive
• Machine Learning Interpretability: A Survey on Methods and Metrics#10579OpenAlex
• Arithmetical realizations of modal formulas. Preliminary version.#629608GUPEA
• Arithmetical realizations of modal formulas. Preliminary version.#411738GUPEA
• Category-Theoretic Wanderings into Interpretability#86601PhilArchive
• Propositional interpretability in artificial intelligence#103033PhilArchive
• Mechanistic Interpretability Needs Philosophy#225482PhilArchive
• AIMO Interpretability Challenge#370365arXiv CS
• Logicism, Interpretability, and Knowledge of Arithmetic#776229PhilArchive
• Interpretability of machine learning‐based prediction models in healthcare#335863OpenAlex
• Provability logics for relative interpretability#775295PhilArchive
• Test-Retest Reliability, Responsiveness and Interpretability of CLEFT-Q#893074ClinicalTrials.gov
• Concept-based interpretability of foundation models for medical research in immuno-inflammation#326163HAL (France)
• On Interpretability of Artificial Neural Networks: A Survey#686515OpenAlex
• On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)#6465OpenAlex
• Interpretability (Propositional and Mechanistic) Needs Behavior#165238PhilArchive
• Mechanistic Interpretability and Representationalism about Belief#170268PhilArchive
• Patch-Effect Graph Kernels for LLM Interpretability#168368arXiv CS
• Enhancing Interpretability in Distributed Constraint Optimization Problems#715322PhilArchive
• Real Sparks of Artificial Intelligence and the Importance of Inner Interpretability#111971PhilArchive
• Verifying Machine Learning Interpretability Requirements through Provenance#126531arXiv CS
• Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs#353001arXiv CS
• Xeno-Interpretability: Investigating the Alien Minds of LLMs#978483arXiv CS
• Transparency and Interpretability in Cloud- based Machine Learning with Explainable AI#75917PhilArchive
• Sparse Stimulus Generation Improves Reverse Correlation Efficiency and Interpretability#131010bioRxiv / medRxiv
• Agentic-imodels: Evolving agentic interpretability tools via autoresearch#155297arXiv CS
• Heart failure risk prediction based on machine learning and interpretability analysis.#258210NCBI PubMed Central
• Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability#259484arXiv CS
• Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations#303262arXiv CS
• KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability#405684arXiv CS
• Meta-Theories, Interpretability, and Human Nature: A Reply to J. David Velleman#765528PhilArchive
• Interpretability for Turing Machines#927928arXiv (All)
• Flag Game: A Toy Model for Mechanistic Swarm Interpretability#965449arXiv CS
• Structural interpretability in SVMs with truncated orthogonal polynomial kernels#18996arXiv CS
• When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers#224412arXiv CS
• Critical Percolation as a Synthetic Data Model for Interpretability#290593arXiv CS
• Interpretability in Deep Time Series Models Demands Semantic Alignment#650739arXiv (OAI Expanded)
• Interpretability in Deep Time Series Models Demands Semantic Alignment#652192arXiv (All)
• The Enhanced Indispensability Argument, the circularity problem, and the interpretability strategy#739901PhilArchive
• Efficient Auto-Interpretability of AI Models in Biology#779674arXiv (OAI Expanded)
• Efficient Auto-Interpretability of AI Models in Biology#781049arXiv (All)
• A systematic review on the integration of explainable artificial intelligence in intrusion detection systems to enhancing transparency and interpretability in cybersecurity#671718OpenAlex
• Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures#326510IRIS
• Improving clinical interpretability of linear neuroimaging models through feature whitening#124059arXiv CS
• Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs#128231arXiv CS