An argument paper reframes LLM explainability as an embodied, situated practice based on Dourish and enactivist cognition, identifying ontological obstacles in internal explanations and advocating affordance-based designs.
hub Canonical reference
Towards A Rigorous Science of Interpretable Machine Learning
Canonical reference. 71% of citing Pith papers cite this work as background.
74
Pith papers citing it
Background
71% of classified citations
abstract
As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.
hub tools
citation-role summary
background 13
method 1
citation-polarity summary
representative citing papers
Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.
ISAAC auditing applied to three DTI models on the Davis benchmark finds 25% relative differences in causal reasoning scores despite nearly identical AUROC values.
In-context symbolic regression methods improve robustness of symbolic formula recovery from KANs, cutting median OFAT test MSE by up to 99.8 percent across hyperparameter sweeps.
Qualitative study of 19 practitioners reveals ten LLM product evaluation practices and introduces the results-actionability gap as a key barrier to turning findings into improvements.
A training-free method using Fourier-parameterized star-convex contours optimized via gradients to generate compact, faithful visual attributions for image classifiers on benchmarks like ImageNet.
A method automatically constructs a causal model from behavior tree structure and domain knowledge to generate real-time causal counterfactual explanations for robot decisions.
SAE-NOs extend sparse autoencoders to function spaces via Fourier neural operators with concept and domain sparsity, learning localized patterns more efficiently and generalizing across discretizations on vision data.
MIMIC is a new inversion framework that recovers visual concepts from VLM internal states using joint inversion, feature alignment, and three regularizers.
Chain-of-thought explanations in LLMs are frequently unfaithful: models systematically omit mention of biasing prompt features that change their answers and instead produce rationalizations for those biased outputs.
AI models misalign with humans on concept boundaries when probed with implausible category members, such as classifying words as vehicles or vegetables as fruit.
p-ResNet-50 adds a prototype layer with anchor- and medoid-based regularizations to ResNet-50, achieving ROC-AUC 0.994 and accuracy 0.957 on ~12k XCT patches while supplying case-based explanations aligned to expert categories.
The authors introduce a taxonomy with target, functional role, and mode of justification axes plus a framework that decomposes abstract XAI desiderata into concrete benchmarkable tasks via identified dependency structures.
An entropy criterion on mean representations characterises the polarised regime in VAEs and related models, with theoretical links to KL minimisation and empirical tests across several architectures.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
AI deployment in high-stakes areas requires domain-scoped calibrated verification with monitoring and revocation, using a proposed six-component Verification Coverage standard instead of mechanistic interpretability.
ShifaMind achieves competitive performance with the LAAT baseline on MIMIC-IV top-50 ICD-10 coding while outperforming vanilla concept bottleneck models and providing concept-mediated explanations.
The authors introduce the XAI Evaluation Card template to standardize how XAI evaluation metrics are defined, validated, and reported.
NEURON raises AUC from 0.74-0.77 to 0.84-0.88 on MIMIC-IV heart-failure mortality prediction while lifting human-aligned explanation scores from 0.50 to 0.85 by grounding SHAP values in SNOMED CT and patient notes via RAG-LLM.
In high-stakes settings, Shapley explanations increase analyst confidence but do not improve decision accuracy, and standard metrics fail to predict human utility.
A four-year mixed-methods study of game-based systems for Indian CHWs yields eight design guidelines for sustained engagement, learning transfer, and contextual appropriateness in low-resource health training.
X-SYS is a reference architecture for interactive explanation systems organized around STAR quality attributes and five service components, demonstrated via SemanticLens for vision-language models.
FaVeX accelerates verified explanations for neural networks via dynamic batch-sequential processing and query reuse while introducing verifier-optimal robust explanations that incorporate verifier incompleteness.
citing papers explorer
-
ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction
ISAAC auditing applied to three DTI models on the Davis benchmark finds 25% relative differences in causal reasoning scores despite nearly identical AUROC values.
-
In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
In-context symbolic regression methods improve robustness of symbolic formula recovery from KANs, cutting median OFAT test MSE by up to 99.8 percent across hyperparameter sweeps.
-
Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models
An entropy criterion on mean representations characterises the polarised regime in VAEs and related models, with theoretical links to KL minimisation and empirical tests across several architectures.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Interpretability Can Be Actionable
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
-
ShifaMind: A Multiplicative Concept Bottleneck for Interpretable ICD-10 Coding
ShifaMind achieves competitive performance with the LAAT baseline on MIMIC-IV top-50 ICD-10 coding while outperforming vanilla concept bottleneck models and providing concept-mediated explanations.
-
Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
In high-stakes settings, Shapley explanations increase analyst confidence but do not improve decision accuracy, and standard metrics fail to predict human utility.
-
NeuroViz: Real-time Interactive Visualization of Forward and Backward Passes in Neural Network Training
NeuroViz offers interactive real-time visualization of neural network forward and backward passes, achieving top usability scores in a study with 31 participants compared to existing tools.
-
Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference
Multimodal anomaly detection must be reframed as cross-modal contextual inference that separates context from observations to define abnormality conditionally.
-
Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms
The paper delivers a mechanism-centric taxonomy and unified perspective on explainable human activity recognition methods across sensing modalities.
-
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
An event-centric framework encodes environments as semantic events and retrieves weighted prior maneuvers from a knowledge bank to enable interpretable, physics-aware decision-making for UAVs.
-
Explainability Methods for Hardware Trojan Detection: A Systematic Comparison
Compares domain-aware, case-based, and feature attribution explainability methods for gate-level hardware Trojan detection on the Trust-Hub benchmark dataset.
- I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models
- Towards interpretable AI with quantum annealing feature selection