The Quarrel of Local Post-hoc Explainers for Moral Values Classification in Natural Language Processing

Although popular and effective, large language models (LLM) are characterised by a performance vs. transparency trade-off that hinders their applicability to sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations recently proposed by the XAI community. However, to the best of our knowledge,...

Metrics for Evaluating Explainable Recommender Systems

Recommender systems aim to support their users by reducing information overload so that they can make better decisions. Recommender systems must be transparent, so users can form mental models about the system’s goals, internal state, and capabilities, that are in line with their actual design. Explanations and transparent behaviour of the...

A General-Purpose Protocol for Multi-agent Based Explanations

Building on prior works on explanation negotiation protocols, this paper proposes a general-purpose protocol for multi-agent systems where recommender agents may need to provide explanations for their recommendations. The protocol specifies the roles and responsibilities of the explainee and the explainer agent and the types of information...

A Design Pattern Language for Hybrid Intelligent Teams

The field of Hybrid Intelligence (HI) is like a vast land with many tribes that speak different languages. Our goal is to develop a lingua franca to unify the peoples of the HI land.We expect our language to facilitate documentation and communication of research results and thus collaboration among various HI fields by making use of design...

Efficient Training of Robust Decision Trees Against Adversarial Examples

Recently it has been shown that many machine learning models are vulnerable to adversarial examples: perturbed samples that trick the model into misclassifying them. Neural networks have received much attention but decision trees and their ensembles achieve state-of-the-art results on tabular data, motivating research on their robustness....

Using Bisimulation Metrics to Analyze and Evaluate Latent State Representations

Deep Reinforcement Learning (RL) is a promising technique towards constructing intelligent agents, but it is not always easy to understand the learning process and the factors that impact it. To shed some light on this, we analyze the Latent State Representations (LSRs) that deep RL agents learn, and compare them to what such agents should...

Reinforcement Learning-Based Persuasion by a Conversational Agent for Behavior Change

Active Monitoring of Neural Networks

Neural-network classifiers are trained to achieve high prediction accuracy. However, their performance still suffers from frequently appearing inputs of unknown classes. As a component of a cyber-physical system, the classifier in this case can no longer be reliable and is typically retrained. We propose an algorithmic framework for monitoring...

Localised Reputation in the Prisoner’s Dilemma

Under what conditions can cooperation emerge and be sustained? Previous studies abstract cooperation and defection using the spatial Prisoner’s Dilemma (PD) game. We study a local reputation mechanism in which agents can remember defectors, abstain from interacting with them, and warn nearby agents. Simulations find that local reputation is...

Online Learning of Deeper Variable Ordering Heuristics for Constraint Optimisation Problems

Solvers for constraint optimisation problems exploit variable and value ordering heuristics. Numerous expert-designed heuristics exist, while recent research uses machine learning to learn novel heuristics. We introduce the concept of deep heuristics, a data-driven approach to learn extended versions of a given variable ordering heuristic. We...

Agent-Based Simulation of Short-Term Peer-to-Peer Rentals: Evidence from the Amsterdam Housing Market (Article Abstract)

The full article published in Environment and Planning B studies the effect of a range of possible municipal policy measures on the peer-to-peer short-term rental market. The case study is the city of Amsterdam. A spatial agent-based simulation indicates that more lower income citizens remain in the city centre when regulation of the market is...

A Two-Dimensional Explanation Framework to Classify AI as Incomprehensible, Interpretable, or Understandable

Because of recent and rapid developments in Artificial Intelligence (AI), humans and AI-systems increasingly work together in human-agent teams. However, in order to effectively leverage the capabilities of both, AI-systems need to be understandable to their human teammates. The branch of eXplainable AI (XAI) aspires to make AI-systems more...