State of the Field
Recent advances in explainable AI are focusing on enhancing the interpretability and reliability of machine learning models across various applications. A notable trend is the integration of counterfactual explanations into training regimes, which allows models to generate actionable insights that align with user preferences and decision-making constraints. This shift is particularly relevant in sectors like e-commerce and fraud detection, where understanding model behavior is crucial for trust and accountability. Additionally, new frameworks are emerging that combine collaborative filtering with language models to improve recommendation systems, ensuring that explanations are not only factually correct but also resonate with user intent. The development of methods that address fairness in counterfactual explanations highlights the growing recognition of ethical considerations in AI deployment. Overall, the field is moving towards solutions that prioritize both transparency and user-centric design, addressing commercial challenges while fostering trust in AI systems.
Papers
1–10 of 17Reasoning-guided Collaborative Filtering with Language Models for Explainable Recommendation
Large Language Models (LLMs) exhibit potential for explainable recommendation systems but overlook collaborative signals, while prevailing methods treat recommendation and explanation as separate task...
ECSEL: Explainable Classification via Signomial Equation Learning
We introduce ECSEL, an explainable classification method that learns formal expressions in the form of signomial equations, motivated by the observation that many symbolic regression benchmarks admit ...
Counterfactual Training: Teaching Models Plausible and Actionable Explanations
We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as...
Process-Guided Concept Bottleneck Model
Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relatio...
Provably Robust Bayesian Counterfactual Explanations under Model Changes
Counterfactual explanations (CEs) offer interpretable insights into machine learning predictions by answering ``what if?" questions. However, in real-world settings where models are frequently updated...
XChoice: Explainable Evaluation of AI-Human Alignment in LLM-based Constrained Choice Decision Making
We present XChoice, an explainable framework for evaluating AI-human alignment in constrained decision making. Moving beyond outcome agreement such as accuracy and F1 score, XChoice fits a mechanism-b...
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game theory. However, in pra...
Extended Empirical Validation of the Explainability Solution Space
This technical report provides an extended validation of the Explainability Solution Space (ESS) through cross-domain evaluation. While initial validation focused on employee attrition prediction, thi...
Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation
LLM-based explainable recommenders can produce fluent explanations that are factually correct, yet still justify items using attributes that conflict with a user's historical preferences. Such prefere...
Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations
Explainable Artificial Intelligence (XAI) is becoming increasingly essential for enhancing the transparency of machine learning (ML) models. Among the various XAI techniques, counterfactual explanatio...