Search research

Topics & fields

Mechanistic Interpretability435 papers Model Interpretability269 papers Mechanistic Interpretability159 papers Interpretable Models38 papers Interpretable Diabetic Retinopathy Grading25 papers Interpretive Openness25 papers

871–900 of 6,027

Papers

AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks
May 14, 2026Magdalena Proszewska, N. SiddharthExplainability Graph Neural Networks
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
May 14, 2026Tommaso Mencattini, Francesco Montagna, Francesco LocatelloSemantic Representations Mechanistic Interpretability
Towards Fine-Grained and Verifiable Concept Bottleneck Models
May 14, 2026Yingying Fang, Haijie Xu, Shuang Wu +2Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
Multimodal Hidden Markov Models for Persistent Emotional State Tracking
May 13, 2026Anamika Ragu, Aneesh JonelagaddaEmotion Recognition Valence-Arousal Estimation
A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data
May 12, 2026Ziwei Huang, Zeyuan Song, Paola Sebastiani +1Complex Networks High-Dimensional Data
BoolXLLM: LLM-Assisted Explainability for Boolean Models
May 12, 2026Du Cheng, Serdar Kadioglu, Xin WangExplainability Xai
Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention
May 12, 2026Gabriel Curtosi, Carlos Manuel Ruiz Ruiz, Fabiola Cavaliere +1Crashes Accidents
Deep Arguing
May 11, 2026Adam Gould, Francesca ToniDeep Learning Abstract Argumentation
Causal Explanations from the Geometric Properties of ReLU Neural Networks
May 11, 2026Hector Woods, Philippa Ryan, Rob AlexanderRectified Linear Unit Networks Causal Reasoning
Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning
May 10, 2026Siyu Wu, Cong Xu, Wei ZhangPer-Competency Bayesian Knowledge Tracing Reasoning Traces
Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-wise Adaptive Regularization Approach
May 9, 2026Hira Nasir, Eiman Javed, Balawal Shabir +2Intrusion Detection Adversarial Transferability
Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
May 8, 2026Gajendra Katuwal, Advait Koparkar, Salar Abbaspourazad +2Electronic Health Record Foundation Models Multimodal Foundation Model
Bridging Textual Profiles and Latent User Embeddings for Personalization
May 7, 2026Zhaoxuan Tan, Xiang Zhai, Yan Zhu +2Recommender Systems Multimodal Recommendation
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
May 7, 2026Claire Chen, Jiabao Sean Xiao, Shuze Daniel Liu +7Multimodal Benchmarks Multimodal Classification
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
May 6, 2026Joshua C. ChangLogistic Regression Renormalization Group
Cross-Model Consistency of Feature Importance in Electrospinning: Separating Robust from Model-Dependent Features
May 6, 2026Mehrab Mahdian, Ferenc Ender, Tamas PardyFeature Importance Machine Learning
Measuring Psychological States Through Semantic Projection: A Theory-Driven Approach to Language-Based Assessment
May 6, 2026Maria Luongo, Davide Marocco, Nicola MilanoPsychology
GRAFT: Auditing Graph Neural Networks via Global Feature Attribution
May 5, 2026Rishi Raj Sahoo, Subhankar MishraGraph Neural Networks Subgraphs
FLoRA: Fusion-Latent for Optical Reconstruction and Flood Area Segmentation via Cross-Modal Multi-Task Distillation Network
May 4, 2026Jagrati Talreja, Tewodros Syum Gebre, Leila Hashemi-BeniFlood Detection Sen1Floods11
GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
May 3, 2026Favour Nerrise, Lucy Yin, Mohammad H. Abbasi +2Improving Sparse Autoencoders Anatomical Priors
Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignment
May 1, 2026Xinran Liu, Yuwen Li, Hongxiang Gao +4Pediatric-Adult Electrocardiogram Alignment Intensive Care Unit
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Apr 29, 2026Madhumitha Venkatesan, Xuyang Chen, Dongyu LiuTime-Series Classification Chart
Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations
Apr 28, 2026Chen Liang, Xirui Jiang, Naihao Deng +2Ava-Vlm User Interface
An Information-Geometric Framework for Stability Analysis of Large Language Models under Entropic Stress
Apr 27, 2026Hikmat Karimov, Rahid Zahid AlekberliLarge Language Model Output Artificial Intelligence Safety
MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks
Apr 26, 2026Jui-Cheng Chiu, Yu-Chao Wang, Shengyang Luo +4Explicit Visual Grounding Visual Storytelling
Modeling Induced Pleasure through Cognitive Appraisal Prediction via Multimodal Fusion
Apr 26, 2026Nastaran Dab, Raziyeh Zall, Mohammadreza KangavariAffective Computing Multimodal Fusion
Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension
Apr 26, 2026Ping LiTransformer Architectures
REC-CBM: Rubric-Aware Error-Correction Concept Bottleneck Models for Trustworthy Open-Ended Grading
Apr 24, 2026Chengshuai Zhao, Fan Zhang, Kumar Satvik Chaudhary +4Grading Concept Bottleneck Models
Audio Video Verbal Analysis (AVVA) for Capturing Classroom Dialogues
Apr 23, 2026Vivek Upadhyay, Amaresh Chakrabarti
Locating acts of mechanistic reasoning in student team conversations with mechanistic machine learning
Apr 23, 2026Kaitlin Gili, Mainak Nistala, Kristen Wendell +1Mechanistic Interpretability Interpretable Models

May 14, 2026 · cs.LGJ/K move · Enter open · S save

AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks

Magdalena Proszewska, N. Siddharth

School of Informatics, University of Edinburgh

Graph Neural Networks (GNNs) have advanced significantly in handling graph-structured data, but a comprehensive framework for evaluating explainability remains lacking. Existing evaluation frameworks primarily involve post-hoc explanations, and operate in the setting where multiple methods generate a suite of explanations for a single model. This makes comparison of explanations across models difficult. Evaluation of inherently interpretable models often targets a specific aspect of interpretability relevant to the model, but remains underdeveloped in terms of generating insight across a suite of measures. We introduce AIM, a comprehensive framework that addresses these limitations by measuring Accuracy, Instance-level explanations, and Model-level explanations. AIM is formulated with minimal constraints to enhance flexibility and facilitate broad applicability. Here, we use AIM in a pipeline, extracting explanations from inherently interpretable GNNs such as graph kernel networks (GKNs) and prototype networks (PNs), evaluating these explanations with AIM, identifying their limitations and obtaining insights to their characteristics. Taking GKNs as a case study, we show how the insights obtained from AIM can be used to develop an updated model, xGKN, that maintains high accuracy while demonstrating improved explainability. Our approach aims to advance the field of Explainable AI (XAI) for GNNs, providing more robust and practical solutions for understanding and improving complex models.

Explainability Graph Neural Networks Graph Representations

Open paper Ask about it PDF