Explainable AI Methods

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 10% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21

Latest papers 230

All topics

Beyond a Single Explanation of the Adam--SGD Gap
Jun 12, 2026Chenxiang Zhang, Rustem Islamov, Enea Monzio Compagnoni +3Adam Explainable AI Methods
University of Luxembourg · MPI for Intelligent Systems · University of Basel +2
Position: Align AI to Our Aspirations, Not Our Flaws
Jun 11, 2026Nikita Kazeev, Bui Nhat Huyen PhanPluralistic Alignment Internal Pluralism
1National University of Singapore · 2Shopee Singapore.
Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
Jun 10, 2026Darpan Aswal, Thomas Palmeira Ferraz, Yongxin Zhou +1Latent Thoughts Intermediate Latent States
Université Grenoble Alpes, CNRS, Grenoble INP, LIG · Université Paris-Saclay · NAVER LABS Europe
Forecasting Future Behavior as a Learning Task
Jun 9, 2026Mosh Levy, Yoav Goldberg, Asa Cooper SticklandLarge Language Model Forecasting Reasoning Trajectory
Bar-Ilan University · Constellation · UK AI Security Institute +1
Large Language Models as Modal Models in Linguistics
Jun 9, 2026Haruto Suzuki, Saku SugawaraLinguistics Multimodal Large Language Models
1Keio University · 2National3UniversityInstituteofofTokyo
Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Models
Jun 9, 2026Vinícius Peixoto Chagas, Carlos Henrique Leitão Cavalcante, Thiago Alves RochaExplainability Explainable AI Methods
Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
Jun 5, 2026Manuele LeonelliExplainability Explainable AI Methods
School of Science and Technology, IE University, Madrid, Spain
Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses
Jun 5, 2026Indu Panigrahi, Tal AugustLarge Language Model Responses Large Language Model Evaluation
Siebel School of Computing and Data Science University of Illinois Urbana-Champaign
Explainably Safe Reinforcement Learning
Jun 3, 2026Sabine Rieder, Stefan Pranger, Debraj Chakraborty +2Offline Reinforcement Learning Explainable AI Methods
Masaryk University · Technical University of Munich · Graz University of Technology
Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales
May 31, 2026Pingjun Hong, Benjamin RothExplainable AI Methods Free-Form Textual Rationales
Faculty of Computer Science, University of Vienna, Vienna, Austria · UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria · Faculty of Philological and Cultural Studies, University of Vienna, Vienna, Austria
Counterfactual Explanations for Deep Two-Sample Testing
May 29, 2026Wei-Cheng Lai, Marco Simnacher, Christoph LippertTwo-Sample Testing Counterfactual Explanation
Digital Health and Machine Learning Hasso-Plattner-Institute, University of Potsdam Potsdam, Germany · Chair of Statistics Humboldt-Universität zu Berlin Berlin, Germany · Hasso Plattner Institute for Digital Health at Mount Sinai Icahn School of Medicine at Mount Sinai New York, United States of America
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
May 29, 2026Salim I. Amoukou, Emanuele Albini, Tom Bewley +2Domain Adaptation Distribution Shifts
J.P. Morgan AI Research
Xetrieval: Mechanistically Explaining Dense Retrieval
May 28, 2026Zhixin Cai, Jun Bai, Yang Liu +7Retrieval Layer Text Embeddings
School of Computer Science and Engineering, Beihang University · 2State Key Laboratory of General Artificial Intelligence, BIGAI
Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation
May 27, 2026Neemias da Silva, Matt Ratto, Myriam Delgado +3Artificial Intelligence Personas Persona Consistency
University of Toronto, Toronto, Canada · Universidade Tecnologica Federal do Parana, Curitiba, Brazil
Ontology-Guided Reasoning for Affordance-Based Explanations of Robot Navigation
May 27, 2026Amar Halilovic, Vahidin Hasic, Senka KrivicSemantic-Affordance Inference Robot Navigation
Institute of Artificial Intelligence, Ulm University, 89081 Ulm, Germany · Faculty of Electrical Engineering, University of Sarajevo, 71000 Sarajevo, BiH
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
May 27, 2026Carmen Quiles-Ramírez, Leticia L. Rodríguez, Nicolás Martorell +1Explainability Multimodal Large Language Models
Universidad de Granada, Spain · Universidad de Buenos Aires, Argentina
Auditing Stance Asymmetry in Generative Explanations
May 27, 2026Jiarui HanLarge Language Model Bias Asymmetry
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
May 26, 2026Tomás Pereira, João Vitorino, Eva Maia +1Explainability Explainable AI Methods
GECAD, ISEP, Polytechnic of Porto, Porto, Portugal
Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
May 26, 2026Fabian Lukassen, Jan Herrmann, Christoph Weisser +3Xai Explainable Artificial Intelligence
University of Göttingen · BASF SE · Hochschule Bielefeld +1
Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations
May 25, 2026Eduardo Luiz Alba, Gilson Adamczuk Oliveira, Matheus Henrique Dal Molin Ribeiro +1Electricity Price Forecasting Shapley Additive Explanations
Industrial & Systems Engineering Graduate Program (PPGEPS), Federal University of Technology-Parana (UTFPR), Via do Conhecimento, KM 0l—Fraron, Pato Branco 85503-390, PR, Brazil
They Are Not the Same: Direct Causes Are Not Grounded Emotion Explanations
May 24, 2026Zhuangzhuang Pan, Yan Xia, Chee Seng ChanEmotion Explainable AI Methods
Universiti Malaya, Malaysia · Suzhou University of Technology, China · VinUniversity, Vietnam
Re-defining Humor Data Objects for AI Humor Research
May 24, 2026Anna Arnett, Bang Nguyen, Meng JiangHumor Explainable AI Methods
Department of Computer Science and Engineering, University of Notre Dame
Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants
May 23, 2026Emanuele Guidotti, Sara PuglioliMolecular Representation Learning Chemical Structures
University of Lugano, Switzerland · Philochem AG, Switzerland
Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
May 22, 2026David Boetius, Shahaf Bassan, Guy Katz +2Shapley Value Shapley Additive Explanations
University of Konstanz, Konstanz, Germany · Hebrew University of Jerusalem, Jerusalem, Israel · University of St.Gallen, St.Gallen, Switzerland.
Human Decision-Making with Persuasive and Narrative LLM Explanations
May 22, 2026Laura R. Marusich, Mary Grace Kozuch Dhooghe, Jonathan Z. Bakdash +1Large Language Model Decisions Persuasion
DEVCOM Army Research Laboratory Adelphi, MD 20783 · University of Texas at Dallas Richardson, TX 75080 · Virginia Polytechnic Institute and State University Blacksburg, VA 24060
Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
May 21, 2026Helena Merker, Nick Walker, Andreea BobuReward Functions Robot Systems
Massachusetts Institute of Technology
Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
May 21, 2026Neel SomaniTransformer Architectures Interpretability
Independent Researcher
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
May 21, 2026Sungjun Lim, Heedong Kim, Andrew Lee +1Interpretability Mechanistic Interpretability
aYonsei University · bHarvard University
Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
May 20, 2026Jacek Karolczak, Jerzy StefanowskiFeature Importance Interpretability
Institute of Computing Science Poznan University of Technology ul. Piotrowo 2, 60-965 Pozna´n, Poland
Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education
May 20, 2026Arun-Balajiee Lekshmi-Narayanan, Mohammad Hassany, Peter BrusilovskyAi-Assisted Programming Tasks Explainable AI Methods
University of Pittsburgh
ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
May 19, 2026Hongjiang Chen, Xin Zheng, Pengfei Jiao +5Temporal Graph Neural Networks Interpretability
Hangzhou Dianzi University, Hangzhou, China · RMIT University, Melbourne, Australia · Tianjin University, Tianjin, China +1
Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
May 19, 2026Somnath Banerjee, Pranav Jha, Rima Hazra +1Explainable AI Methods Cross-Lingual Consistency
Indian Institute of Technology Kharagpur · TCG Crest · National University of Singapore
MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation
May 18, 2026Bizhu Wu, Jinheng Xie, Wenting Chen +5Motion Merge
Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China · Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China · School of Computer Science, University of Nottingham Ningbo China +4
Learning Quantifiable Visual Explanations Without Ground-Truth
May 18, 2026Amritpal Singh, Andrey Barsky, Mohamed Ali Souibgui +2Xai Explainable Artificial Intelligence
Computer Vision Center, Barcelona, Spain · Autonomous University of Barcelona, Spain
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
May 18, 2026Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +1Shapley Additive Explanations Explainability
EDF R&D, SINCLAIR Lab · Université de Toulouse · Sorbonne Université +2
iPOE: Interpretable Prompt Optimization via Explanations
May 18, 2026Jiahui Li, Yarik Menchaca Resendiz, Sean Papay +1Prior Prompt Optimization Techniques Prompt Engineering
Fundamentals of Natural Language Processing, University of Bamberg, Germany · Leibniz-Institut für Psychologie (ZPID), Trier, Germany
Counterfactual Explanations Under Concept Drift
May 17, 2026Marcin Kostrzewa, Jerzy Stefanowski, Maciej ZiębaCounterfactual Explanation Explainable AI Methods
Wrocław University of Science and Technology · Pozna´n University of Technology · Tooploox
UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
May 17, 2026Hyunju Kang, Geonhee Han, Hogun ParkCounterfactual Explanation Graph Representation Learning
Department of Artificial Intelligence Sungkyunkwan University Suwon, Republic of Korea
Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
May 16, 2026Toshinori Yamauchi, Hiroshi Kera, Kazuhiko KawamotoExplainability Explainable AI Methods
Chiba University · National Institute of Informatics
Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations
May 15, 2026Narges Babadi, Hadis KarimipourExplainable AI Methods Heatmap
Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada.
Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning
May 15, 2026Yuyuan Liu, Can Peng, Yingyu Yang +3Cone-Beam Computed Tomography Unified Framework
Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
May 14, 2026Thodoris Lymperopoulos, Denia KanellopoulouNeural Network Deep Learning Architectures
NCSR Demokritos Athens, Greece
INSIGHTS: Demonstration-Based Summaries of Time Series Predictors
May 13, 2026Bar Eini Porat, Rom Gutman, Uri Shalit +1Time Series Explainability
Technion Israel Institute of Technology · Tel-Aviv University
Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features
May 13, 2026Jordan F. McCannSparse Autoencoder Features Model Activations
Independent Researcher
AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers
May 12, 2026Raj Kiran Gupta KatakamGradient-Weighted Class Activation Mapping Feature Learning
Credit Karma, San Francisco, CA, USA
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
May 12, 2026ShiYing Huang, Liang Lin, Yuer Li +6Preference Alignment Multi-Objective Reinforcement Learning
Huazhong University of Science and Technology · Nanyang Technological University · Tsinghua University +1
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
May 12, 2026Yilong Wang, Qianli Wang, Bohao Chu +3Large Language Model Alignment Counterfactual Explanation
1Technische Universität Berlin · 2German Research Center for Artificial Intelligence (DFKI) · University of Duisburg-Essen +5
A Controlled Counterexample to Strong Proxy-Based Explanations of OOD Performance: in a Fixed Pretraining-and-Probing Setup
May 12, 2026Hongmin LiGeneration Provenance Out-Of-Distribution
School of Life Science and Technology, Institute of Science Tokyo · Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
May 11, 2026Joel Rorseth, Parke Godfrey, Lukasz Golab +2Large Language Model Safety Explainable AI Methods
University of Waterloo · York University · AT&T Chief Data Office
Causal Explanations from the Geometric Properties of ReLU Neural Networks
May 11, 2026Hector Woods, Philippa Ryan, Rob AlexanderRectified Linear Unit Networks Causal
Department of Computer Science University of York York, United Kingdom
APEX: Audio Prototype EXplanations for Classification Tasks
May 11, 2026Piotr Kawa, Kornel Howil, Piotr Borycki +3Audio Understanding Audio Editing
Department of Artificial Intelligence, Wroclaw University of Science and Technology, Poland · IDEAS Research Institute, Poland · Faculty of Mathematics and Computer Science, Jagiellonian University, Poland +1
Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
May 11, 2026Mateusz Cedro, Marcin ChlebusExplainability Vision Foundation Models
University of Antwerp, Antwerp, 2000, Belgium · University of Warsaw, Warsaw, 00-241, Poland
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
May 11, 2026Gideon Popoola, John SheppardExplainable Artificial Intelligence Algorithmic Fairness
Montana State University, Bozeman, Montana, USA
Attribution-based Explanations for Markov Decision Processes
May 10, 2026Paul Kobialka, Andrea Pferscher, Francesco Leofante +3Markov Decision Processes Explainable AI Methods
University of Oslo, Norway · Imperial College London, United Kingdom · RWTH Aachen University, Germany
Detect, Localize, and Explain: Interactive Hierarchical Log Anomaly Analytics with LLM Augmentation
May 9, 2026Lei Ma, Suhani Chaudhary, Ethan Shanbaum +5Interpretable Anomaly Detection Bug Detection
Worcester Polytechnic Institute, USA · UC Riverside, USA · University of Nevada, Las Vegas, USA
Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations
May 9, 2026Leopoldo BertossiXai Explainable Artificial Intelligence
Carleton University, Canada · IMFD, Chile · Emeritus Professor. Adjunct Professor Western University, Canada.
Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations
May 9, 2026Shanshan Zhu, Han Zhang, J. Doris Chi +2Explainable AI Methods LLM Reasoning Strategies
University of Illinois Urbana-Champaign, USA · University of Chicago, USA · Yale University, New Haven, CT, USA +2
Effective Explanations Support Planning Under Uncertainty
May 8, 2026Hanqi Zhou, Britt Besch, Charley M. Wu +1Explainable AI Methods Planning
University of Tübingen · Technical University Darmstadt · Max Planck Institute for Biological Cybernetics +2
Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks
May 8, 2026Kyle Higgins, Ivan Laponogov, Dennis Veselkov +1Explainable AI Methods Topology
1Division of Cancer, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK. · Department of Computing, Imperial College London, U.K. · Department of Environmental Health Sciences, Yale University, New Haven, CT, USA.
Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
May 8, 2026Wenxin Tai, Yaqian Liu, Ting Zhong +1Graph Neural Networks Explainability
University of Electronic Science and Technology of China

Jun 12, 2026, cs.LGJ/K move · Enter open · S save

Beyond a Single Explanation of the Adam--SGD Gap

Chenxiang Zhang, Rustem Islamov, Enea Monzio Compagnoni, Jun Pang+2

University of Luxembourg · MPI for Intelligent Systems · University of Basel+2

Adam Explainable AI Methods

Open paper AskPDF arXiv

Prior work has identified several factors that can contribute to the performance gap between Adam and SGD, spanning data aspects, architecture design, and optimization properties. Yet these explanations are often studied in isolation, leaving their relative importance unclear. In this work, we revisit these hypotheses through a controlled empirical study across vision, language, genomics, and graph tasks, spanning modern and classical architectures, and carefully designed training setups. Our results suggest that no single factor consistently explains the Adam--SGD gap. For instance, the Adam advantage can (1) persist under a uniform vocabulary distribution yet nearly disappear under a heavy-tailed one; (2) reverse in favor of SGD in softmax-attention models; and (3) become larger under soft architectural modifications, e.g., when ReLU is replaced by a GeLU nonlinearity. This suggests that the gap arises from nontrivial data and architecture interactions, rather than from a single common factor. Yet, we observe a pattern across our settings: a \emph{crossover batch size} at which the relative advantage shifts from SGD to Adam as the batch size scales. These empirical results are captured by our theoretical gap model, which predicts this batch-size-dependent crossover. Our perspective helps reconcile several existing hypotheses while offering practical insights across domains.

Momentum

Related topics

Latest papers 230