Related papers: State2Explanation: Concept-Based Explanations to B…

A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This renders environmental state and progress towards completing a…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model…

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even…

End-to-end reinforcement learning agents learn a state representation and a policy at the same time. Recurrent neural networks (RNNs) have been trained successfully as reinforcement learning agents in settings like dialogue that require…

As Artificial Intelligence (AI) and Agentic AI become increasingly integrated across sectors such as education and healthcare, it is critical to ensure that Multi-Agent Education System (MAES) is explainable from the early stages of…

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive…

Despite the impressive feats demonstrated by Reinforcement Learning (RL), these algorithms have seen little adoption in high-risk, real-world applications due to current difficulties in explaining RL agent actions and building user trust.…

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

This thesis explores the generation of local explanations for already deployed machine learning models, aiming to identify optimal conditions for producing meaningful explanations considering both data and user requirements. The primary…

Learning by self-explanation is an effective learning technique in human learning, where students explain a learned topic to themselves for deepening their understanding of this topic. It is interesting to investigate whether this…

Humans are capable of attributing latent mental contents such as beliefs or intentions to others. The social skill is critical in daily life for reasoning about the potential consequences of others' behaviors so as to plan ahead. It is…

The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations…

Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activations more interpretable by exposing latent features that often…

Concept-based explanations work by mapping complex model computations to human-understandable concepts. Evaluating such explanations is very difficult, as it includes not only the quality of the induced space of possible concepts but also…

Automated decision-making systems are becoming increasingly ubiquitous, which creates an immediate need for their interpretability and explainability. However, it remains unclear whether users know what insights an explanation offers and,…

Recent advances in agentic systems for data analysis have emphasized automation of insight generation through multi-agent frameworks, and orchestration layers. While these systems effectively manage tasks like query translation, data…

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…