Imagen de Portada

A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mamalakis, Michail, Azevedo, Tiago, Cosentino, Cristian, D'Ercoli, Chiara, Abulikemu, Subati, Sun, Zhongtian, Bethlehem, Richard, Lio, Pietro
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unified Generative Latent Representation for Functional Brain Graphs
por: Abulikemu, Subati, et al.
Publicado: (2025)

Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia
por: Abulikemu, Subati, et al.
Publicado: (2025)

A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation
por: D'Ercoli, Chiara, et al.
Publicado: (2025)

Actionable Interpretability via Causal Hypergraphs: Unravelling Batch Size Effects in Deep Learning
por: Sun, Zhongtian, et al.
Publicado: (2025)

Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI
por: Georgenthum, Hugo, et al.
Publicado: (2025)

The Explanation Necessity for Healthcare AI
por: Mamalakis, Michail, et al.
Publicado: (2024)

Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks
por: Mamalakis, Michail, et al.
Publicado: (2024)

HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
por: Cosentino, Cristian, et al.
Publicado: (2025)

TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering
por: Shen, Yiqing, et al.
Publicado: (2024)

Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers
por: Sun, Bohang, et al.
Publicado: (2025)

HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs
por: Bazaga, Adrián, et al.
Publicado: (2024)

Monet: Mixture of Monosemantic Experts for Transformers
por: Park, Jungwoo, et al.
Publicado: (2024)

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
por: Zhang, Qi, et al.
Publicado: (2024)

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
por: El, Batu, et al.
Publicado: (2025)

MonoLoss: A Training Objective for Interpretable Monosemantic Representations
por: Nasiri-Sarvi, Ali, et al.
Publicado: (2026)

GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning
por: Sun, Zhongtian, et al.
Publicado: (2025)

CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
por: Purves, Carlos, et al.
Publicado: (2026)

DSWB: Progress Update from the AHRI Team | Presented on DSWB 2026 AGM
por: Adnew, Bethlehem
Publicado: (2026)

Measuring and Guiding Monosemanticity
por: Härle, Ruben, et al.
Publicado: (2025)

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
por: Templeton, Adly, et al.
Publicado: (2026)

Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
por: Yan, Hanqi, et al.
Publicado: (2024)

GenRec: Generative Sequential Recommendation with Large Language Models
por: Cao, Panfeng, et al.
Publicado: (2024)

La teoría mineral del crecimiento : la experiencia latinoamericana / Markos Mamalakis
por: Mamalakis, Markos

Estrategias generales de empleo e ingreso / Markos Mamalakis
por: Mamalakis, Markos
Publicado: (1978)

Una estrategia de desarrollo relacionada con los servicios : lgunas consideraciones b sicas / Markos Mamalakis
por: Mamalakis, Markos
Publicado: (1950)

Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
por: Ashworth, Cassidy, et al.
Publicado: (2025)

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
por: Pach, Mateusz, et al.
Publicado: (2025)

Evaluating Sparse Autoencoders for Monosemantic Representation
por: Fereidouni, Moghis, et al.
Publicado: (2025)

How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG System
por: Zuo, Kaiwen, et al.
Publicado: (2025)

Uncovering Neuroimaging Biomarkers of Brain Tumor Surgery with AI-Driven Methods
por: Jimenez-Mesa, Carmen, et al.
Publicado: (2025)

Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification
por: Mamalakis, Michail, et al.
Publicado: (2024)

Unsupervised Pretraining for Fact Verification by Language Model Distillation
por: Bazaga, Adrián, et al.
Publicado: (2023)

The Neuroscience of Transformers
por: Koenig, Peter, et al.
Publicado: (2026)

Language Model Knowledge Distillation for Efficient Question Answering in Spanish
por: Bazaga, Adrián, et al.
Publicado: (2023)

FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
por: Zhu, Max, et al.
Publicado: (2024)

Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Data
por: Zahoor, Sheresh, et al.
Publicado: (2025)

Relación entre la longitud mínima de cable de arrastre a filar y la profundidad de pesca en función de las variables más representativas
por: Ercoli, R.
Publicado: (1986)

Evaluation of chemical characteristics and correlation analysis with pulp browning of advanced selections of apples grown in Brazil
por: Luciana Ercoli
Publicado: (2017)

UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation
por: Shi, Tangqi, et al.
Publicado: (2025)

Wasserstein Hypergraph Neural Network
por: Duta, Iulia, et al.
Publicado: (2025)