#explainable ai
35 papers match
Class-Aware Reinforcement Learning for Counterfactual Explanation Generation
Muhammad Adil Saleem, Syed Ali Raza, Mary-Anne Williams
The paper investigates adding the predicted class of an instance to the reinforcement‑learning state representation for generating counterfactual explanations, showing that this cl…
Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
Xu Zheng, Wei Cheng, Zhuomin Chen +3
The paper presents IB-Forecast, an interpretable multivariate time-series forecasting model that uses an information bottleneck to generate sparse, faithful explanations of predict…
Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations
Roel Visser, Isaac Roberts, Barbara Hammer
The paper proposes Contrastive Concept Importance (CCI), a method that attributes the logit margin between a target and a foil class to automatically extracted visual concepts, pro…
Automated Multilabel Mpox Research Classification with Explainable Transformer Models
Tanjim Taharat Aurpa
The paper develops a BERT‑based multilabel classifier to automatically assign 14,590 Mpox research articles to topics such as outbreaks, vaccination, and epidemiology, and uses SHA…
A Scalable AI-Powered System for Explainable Machine Learning Pipelines in Brain Tumor
Yin Lin, Elena De Martin, Giacomo Conte +6
The paper introduces a web‑based visual analytics platform that integrates cohort management, radiomic feature extraction, and guarded inference with pre‑trained machine learning m…
INCLAIR: Inception-Based Longitudinal Clinical Anomaly Detection with Informed Reasoning
Maxx Richard Rahman, Wolfgang Maass
INCLAIR is a framework that detects anomalies in longitudinal clinical records by scoring observations against multiple historical contexts, aggregating evidence, and producing nat…
FADEx: Feature Attribution and Distortion-based Explanation of Dimensionality Reduction
Lucas Greff Meneses, Evandro S. Ortigossa, Claudio Silva +1
The paper introduces FADEx, a local per-instance feature attribution method that explains how individual features influence the placement of data points in any dimensionality reduc…
Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networks
Md. Kamrul Hossain, Walid Aljoby
The paper proposes MILD, a framework that proactively predicts failures across multiple self‑driving network intents and identifies the true root‑cause using a teacher‑augmented mi…
AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations
Javier Irigoyen, Roberto Daza, Francisco Jurado +5
The paper introduces AIriskEval-edu Demo, a platform that audits the pedagogical quality of K-12 instructional explanations by evaluating five risk dimensions and providing binary…
(EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations
Neta Kirmayer, David Tayouri, Andrés Murillo +3
The paper presents (EC)2, a multi‑agent framework that uses large language models to generate event‑centric, hypothesis‑driven explanations for cybersecurity alerts, improving anal…
Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening
Javad Khoramdel, Farhad Hoseyni, Amirhossein Nikoofard
The paper introduces a lightweight method that adapts a frozen vision model using learnable prompt tokens and an adaptive focal loss to detect mild cognitive impairment from drawin…
CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA
Quoc-Khang Tran, Minh-Thien Nguyen, Phu-An Thai +3
The paper presents a neuro‑symbolic Program‑of‑Thought system that uses a 4B language model to generate symbolic programs (Z3 encodings for regulation queries and Python code for p…
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos +7
The paper presents a YOLO-based deep learning system combined with HiResCAM to automatically identify Ichneumonoidea wasp families from high‑resolution images, achieving over 96% a…
On the Disagreement in Perturbation-based xAI -- Benchmarking Perturbation Choices for Flood Detection from SAR Images
Anastasia Schlegel, Ronny Hänsch
The paper studies how different choices of patch size, shape, and replacement method in perturbation-based explainable AI affect the relevance maps for flood detection using SAR im…
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
Paul Darm, Cem Alpturk, Kenneth Ulrich +3
The paper proposes a method that combines implicit differentiation with GradientSHAP and large language models to generate fast, real-time explanations for industrial process contr…
Towards an Intention Abstraction Layer for Autonomous Industrial Systems
Artan Markaj, Raphael Höfer, Felix Gehlhoff
The paper introduces an Intention Abstraction Layer that uses a large language model and an OWL ontology to convert natural‑language goals into persistent, checkable intentions for…
Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation
Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen +4
The paper proposes a self‑evolving, expert‑in‑the‑loop framework that uses large language models to generate and refine depression symptom annotations aligned with DSM‑5‑TR criteri…
Analytic Abduction: Causal Decomposition and Governed Commitment for Human--AI Coordination
Remo Pareschi
The paper proposes a formal framework for analytic abductive reasoning that models how latent causal factors are jointly considered and only committed to when governance conditions…
Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
Anupa Lodhi
The paper presents an XAI framework that combines an Isolation Forest anomaly detector with SHAP explanations to help internal auditors understand and act on suspicious banking tra…
An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory
Ahmed Omar Salim Adnan, Yogananda Manjunath, Shivanjali Khare
The paper presents an explainable, agentic system that uses summary‑based memory to detect multi‑turn conversational scams, introduces a new benchmark dataset (ConScamBench‑278), a…
Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist
Rebecca Afriyie Sarpong, Daniel Commey
The paper surveys local additive feature‑attribution methods, organizes them into a unified framework based on five design choices, compares them via an axiom‑by‑method matrix, and…
Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models
Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis +4
The paper proposes a framework that evaluates explainability methods like LIME and SHAP across models and datasets using fidelity, simplicity, and stability, and builds a knowledge…
Diagnosing and Mitigating Domain Shift in Permission-Based Android Malware Detection
Md Rafid Islam
The paper studies why permission‑based Android malware detectors suffer performance drops when applied to data from different sources and proposes a hybrid training approach using…
CausalGraphX: A Counterfactual Graph Neural Network Framework for Explainable Systemic Risk Assessment
Rabimba Karanjai, Hemanth Madhavarao, Lei Xu +1
The paper presents CausalGraphX, a framework that combines graph neural networks with counterfactual reasoning to predict and explain systemic risk in financial networks, offering…
One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.