Cover Image

EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Bensmail, Chama
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
by: B, Thackshanaramana
Published: (2026)

Do Two AI Scientists Agree?
by: Fu, Xinghong, et al.
Published: (2025)

PLM-eXplain: Divide and Conquer the Protein Embedding Space
by: van Eck, Jan, et al.
Published: (2025)

XplainAct: Visualization for Personalized Intervention Insights
by: Zhang, Yanming, et al.
Published: (2025)

Joint Training Across Multiple Activation Sparsity Regimes
by: Wang, Haotian
Published: (2026)

Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
by: Maghsoudi, Maryam, et al.
Published: (2026)

When Fairness Metrics Disagree: Evaluating the Reliability of Demographic Fairness Assessment in Machine Learning
by: Alsayed, Khalid Adnan
Published: (2026)

EvoMU: Evolutionary Machine Unlearning
by: Batorski, Pawel, et al.
Published: (2026)

EvoLM: In Search of Lost Language Model Training Dynamics
by: Qi, Zhenting, et al.
Published: (2025)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
by: Cao, Yuan-dong, et al.
Published: (2026)

Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks
by: Abdolali, Maryam, et al.
Published: (2025)

Fair Concurrent Training of Multiple Models in Federated Learning
by: Siew, Marie, et al.
Published: (2024)

"Let's Agree to Disagree": Investigating the Disagreement Problem in Explainable AI for Text Summarization
by: Aswani, Seema, et al.
Published: (2024)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
by: Balagansky, Nikita, et al.
Published: (2025)

Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
by: Manchingal, Shireen Kudukkil
Published: (2025)

Dependable Distributed Training of Compressed Machine Learning Models
by: Malandrino, Francesco, et al.
Published: (2024)

Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance
by: Wu, Junde, et al.
Published: (2026)

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
by: Khanh, Truong Xuan, et al.
Published: (2026)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
by: Wang, Jiachen T., et al.
Published: (2025)

Deep Learning-Based Hypoglycemia Classification Across Multiple Prediction Horizons
by: Cinar, Beyza, et al.
Published: (2025)

Why Inference in Large Models Becomes Decomposable After Training
by: Jin, Jidong
Published: (2026)

Learning Concept Bottleneck Models from Mechanistic Explanations
by: De Santis, Antonio, et al.
Published: (2026)

Mechanistic Neural Networks for Scientific Machine Learning
by: Pervez, Adeel, et al.
Published: (2024)

The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
by: Bell, Samuel J., et al.
Published: (2024)

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
by: Zhong, Haodi, et al.
Published: (2025)

Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning
by: Ganesh, Prakhar, et al.
Published: (2025)

Predicting BWR Criticality with Data-Driven Machine Learning Model
by: Oktavian, Muhammad Rizki, et al.
Published: (2024)

Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
by: Bai, Xiaoyan, et al.
Published: (2025)

eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts
by: Medina, Paulo Mario P., et al.
Published: (2026)

Learning Run-time Safety Monitors for Machine Learning Components
by: Vardal, Ozan, et al.
Published: (2024)

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
by: Guo, Ping, et al.
Published: (2025)

When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
by: Wu, Boqian, et al.
Published: (2026)

Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
by: Di Gioia, Davide
Published: (2026)

A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets
by: Shmuel, Assaf, et al.
Published: (2024)

On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
by: Widener, Michael, et al.
Published: (2025)

Limitations of Using Identical Distributions for Training and Testing When Learning Boolean Functions
by: Pérez-Guijarro, Jordi
Published: (2025)

Statistical and Machine Learning Models for Predicting Fire and Other Emergency Events
by: Sharma, Dilli Prasad, et al.
Published: (2024)

Explaining Machine Learning Predictive Models through Conditional Expectation Methods
by: Ruiz-España, Silvia, et al.
Published: (2026)

Why Gradients Rapidly Increase Near the End of Training
by: Defazio, Aaron
Published: (2025)

EvoForest: A Novel Machine-Learning Paradigm via Open-Ended Evolution of Computational Graphs
by: Yuksel, Kamer Ali, et al.
Published: (2026)