Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
The disagreement problem in explainable machine learning: A practi- tioner’s perspective
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
The C-Score quantifies intra-class explanation consistency for CAM methods via confidence-weighted pairwise soft IoU and detects AUC-consistency dissociation as an early warning for model instability on chest X-ray classification.
Explanation biases in feature attribution methods are systematic products of lexical and positional preferences, with observed trade-offs across models and higher bias in anomalous explanations.
This survey synthesizes XAI methods with surrogate modeling workflows for simulations and outlines a research agenda to embed explainability into simulation-driven design and decision-making.
ToxiTrace combines CuSA for LLM-refined toxic spans, GCLoss for gradient-focused saliency, and ARCL for contrastive toxic/non-toxic boundaries to improve Chinese toxicity classification and explainable span extraction.
An architecture stores XAI explanations persistently in searchable storage and uses RAG to synthesize multiple methods conversationally, cutting hallucination rates by 36% in a FinBERT financial sentiment demo.
citing papers explorer
-
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
-
Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
The C-Score quantifies intra-class explanation consistency for CAM methods via confidence-weighted pairwise soft IoU and detects AUC-consistency dissociation as an early warning for model instability on chest X-ray classification.
-
Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution
Explanation biases in feature attribution methods are systematic products of lexical and positional preferences, with observed trade-offs across models and higher bias in anomalous explanations.
-
Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making
This survey synthesizes XAI methods with surrogate modeling workflows for simulations and outlines a research agenda to embed explainability into simulation-driven design and decision-making.
-
ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection
ToxiTrace combines CuSA for LLM-refined toxic spans, GCLoss for gradient-focused saliency, and ARCL for contrastive toxic/non-toxic boundaries to improve Chinese toxicity classification and explainable span extraction.
-
Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI
An architecture stores XAI explanations persistently in searchable storage and uses RAG to synthesize multiple methods conversationally, cutting hallucination rates by 36% in a FinBERT financial sentiment demo.