Cover Image

When Explanations Lie: Why Many Modified BP Attributions Fail

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sixt, Leon, Granz, Maximilian, Landgraf, Tim
Format:	Preprint
Published:	2019
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

WeiPer: OOD Detection using Weight Perturbations of Class Projections
by: Granz, Maximilian, et al.
Published: (2024)

RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction
by: Heurich, Manuel, et al.
Published: (2026)

TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE
by: Panagiotou, Emmanouil, et al.
Published: (2024)

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
by: Zheng, Guanhua, et al.
Published: (2025)

Lost in Transmission: When and Why LLMs Fail to Reason Globally
by: Schnabel, Tobias, et al.
Published: (2025)

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

When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking
by: Rehman, Mohammad Abdul, et al.
Published: (2025)

Learning Through Noise: Why Subliminal Learning Works and When It Fails
by: Brockers, Vincent C., et al.
Published: (2026)

Why Domain Generalization Fail? A View of Necessity and Sufficiency
by: Vuong, Long-Tung, et al.
Published: (2025)

Why Does Agentic Safety Fail to Generalize Across Tasks?
by: Slutzky, Yonatan, et al.
Published: (2026)

Beyond Attribution: Unified Concept-Level Explanations
by: Liu, Junhao, et al.
Published: (2024)

Missingness Bias Calibration in Feature Attribution Explanations
by: Sridhar, Shailesh, et al.
Published: (2026)

Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
by: Liang, Zida, et al.
Published: (2025)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
by: Achtibat, Reduan, et al.
Published: (2022)

Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
by: Nie, Wenhua, et al.
Published: (2026)

Why Do More Experts Fail? A Theoretical Analysis of Model Merging
by: Wang, Zijing, et al.
Published: (2025)

Why Smooth Stability Assumptions Fail for ReLU Learning
by: Katende, Ronald
Published: (2025)

Why Do Transformers Fail to Forecast Time Series In-Context?
by: Zhou, Yufa, et al.
Published: (2025)

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)

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features
by: McCann, Jordan F.
Published: (2026)

Foundation Models in Radiology: What, How, When, Why and Why Not
by: Paschali, Magdalini, et al.
Published: (2024)

Generative Myopia: Why Diffusion Models Fail at Structure
by: Siami, Milad
Published: (2025)

Sufficient and Necessary Explanations (and What Lies in Between)
by: Bharti, Beepul, et al.
Published: (2024)

Minimizing False-Positive Attributions in Explanations of Non-Linear Models
by: Gjølbye, Anders, et al.
Published: (2025)

Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
by: Matsuno, Ryuta
Published: (2024)

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
by: Qiu, Haiquan, et al.
Published: (2025)

Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
by: Denisov-Blanch, Yegor, et al.
Published: (2026)

Substance Beats Style: Why Beginning Students Fail to Code with LLMs
by: Lucchetti, Francesca, et al.
Published: (2024)

Amortized Variational Inference: When and Why?
by: Margossian, Charles C., et al.
Published: (2023)

When, Where and Why to Average Weights?
by: Ajroldi, Niccolò, et al.
Published: (2025)

When Counterfactual Reasoning Fails: Chaos and Real-World Complexity
by: Aalaila, Yahya, et al.
Published: (2025)

When Vision Fails: Text Attacks Against ViT and OCR
by: Boucher, Nicholas, et al.
Published: (2023)

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
by: Pacela, Vitória Barin, et al.
Published: (2026)

Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
by: Zhang, Zheyuan, et al.
Published: (2026)

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution
by: Wang, Ying, et al.
Published: (2023)

Unifying Attribution-Based Explanations Using Functional Decomposition
by: Gevaert, Arne, et al.
Published: (2024)

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
by: Park, Min-Yeong, et al.
Published: (2025)

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
by: Verine, Alexandre, et al.
Published: (2025)

Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
by: Roy, Dip, et al.
Published: (2026)

Why Alignment Must Precede Distillation: A Minimal Working Explanation
by: Cha, Sungmin, et al.
Published: (2025)