Polynomial-time exact ASV computation for rooted trees via topological equivalence classes, plus sampling approximation for arbitrary causal DAGs.
hub
Artificial Intelligence 267, pp
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
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.
SMX explains spectral ML classifiers by summarizing expert zones with PCA, testing quantile predicates via perturbation, aggregating via directed graph centrality, and reconstructing thresholds back onto original spectra.
Critic-Driven Voronoi State Partitioning distills deep RL policies into piecewise-linear models by iteratively adding linear subpolicies in high-value-error regions identified by the critic.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
A quantitative bipolar argumentation framework with five metrics is proposed to evaluate LLM debate summaries by comparing argument structures extracted from source debates and their summaries.
EXTree structures ABAC policies as trees to enable efficient decisions and actionable explanations for denied access requests.
A qualitative study with 22 creative writers finds that the reflective value of AI refusals depends on alignment with users' situational thinking phases, cognitive beliefs, and views of AI roles.
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
Explores value-level and graph-level aggregation in multi-agent value-based argumentation and proposes aggregating rankings extracted from attack relations as a third method.
A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.
The paper develops a design science framework for governing AI-assisted operational decision support in security operations centers by specifying a query-broker artifact that separates AI planning from execution through approved templates, policy validation, and engineering review gates.
Interval counterfactual explanations outperform point counterfactuals and feature importance scores in boosting model understanding and demonstrated trust according to a within-subjects user study.
Industry markets AI agents for orchestration, creation, and insight, but a usability study with 31 participants reveals users face challenges from capability misalignment and lack of meta-cognition in tools like Operator and Manus.
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
Position paper proposing Model Science as a discipline to systematically analyze AI model behavior beyond benchmarks, drawing analogies from cognitive science, neuroscience, medicine, and agriculture.
LLMs support decision prediction and rationale generation but lack evidence for genuine decision explanation, requiring stricter standards to avoid over-crediting.
A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.
citing papers explorer
-
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Polynomial-time exact ASV computation for rooted trees via topological equivalence classes, plus sampling approximation for arbitrary causal DAGs.
-
Embodied Explainability and Ontological Obstacles: Why We Struggle to Explain the Answers of Large Language Models (LLMs)
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.
-
Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models
SMX explains spectral ML classifiers by summarizing expert zones with PCA, testing quantile predicates via perturbation, aggregating via directed graph centrality, and reconstructing thresholds back onto original spectra.
-
Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
Critic-Driven Voronoi State Partitioning distills deep RL policies into piecewise-linear models by iteratively adding linear subpolicies in high-value-error regions identified by the critic.
-
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.
-
Evaluating LLM-Driven Summarisation of Parliamentary Debates with Computational Argumentation
A quantitative bipolar argumentation framework with five metrics is proposed to evaluate LLM debate summaries by comparing argument structures extracted from source debates and their summaries.
-
EXTree: Towards Supporting Explainability in Attribute-based Access Control
EXTree structures ABAC policies as trees to enable efficient decisions and actionable explanations for denied access requests.
-
Beyond Compliance: How AI Could Help Creative Writers by Refusing Them
A qualitative study with 22 creative writers finds that the reflective value of AI refusals depends on alignment with users' situational thinking phases, cognitive beliefs, and views of AI roles.
-
A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
-
Ethical and social risks of harm from Language Models
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
-
Aggregation in Value-Based Argumentation Frameworks
Explores value-level and graph-level aggregation in multi-agent value-based argumentation and proposes aggregating rankings extracted from attack relations as a third method.
-
A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization
A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.
-
Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support
The paper develops a design science framework for governing AI-assisted operational decision support in security operations centers by specifying a query-broker artifact that separates AI planning from execution through approved templates, policy validation, and engineering review gates.
-
Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations
Interval counterfactual explanations outperform point counterfactuals and feature importance scores in boosting model understanding and demonstrated trust according to a within-subjects user study.
-
Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents
Industry markets AI agents for orchestration, creation, and insight, but a usability study with 31 participants reveals users face challenges from capability misalignment and lack of meta-cognition in tools like Operator and Manus.
-
Explaining Graph Neural Networks for Node Similarity on Graphs
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
-
The Case for Model Science: Verify, Explore, Steer, Refine
Position paper proposing Model Science as a discipline to systematically analyze AI model behavior beyond benchmarks, drawing analogies from cognitive science, neuroscience, medicine, and agriculture.
-
LLMs Should Not Yet Be Credited with Decision Explanation
LLMs support decision prediction and rationale generation but lack evidence for genuine decision explanation, requiring stricter standards to avoid over-crediting.
-
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.