Related papers: Tell me why! Explanations support learning relatio…

Physical construction---the ability to compose objects, subject to physical dynamics, to serve some function---is fundamental to human intelligence. We introduce a suite of challenging physical construction tasks inspired by how children…

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off:…

Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurate predictions, but also in their ability to generate cogent narrative explanations of…

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents…

In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier. Because of the need for explainable agents in automated decision processes, we attempt to interpret the latent…

Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if…

Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories…

It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases…

Large Language Models (LLMs) can produce verbalized self-explanations, yet prior studies suggest that such rationales may not reliably reflect the model's true decision process. We ask whether these explanations nevertheless help users…

Enabling humans to identify potential flaws in an agent's decision making is an important Explainable AI application. We consider identifying such flaws in a planning-based deep reinforcement learning (RL) agent for a complex real-time…

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs in explicit causal reasoning. ExpliCa uniquely integrates…

From the earliest years of our lives, humans use language to express our beliefs and desires. Being able to talk to artificial agents about our preferences would thus fulfill a central goal of value alignment. Yet today, we lack…

The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate…

Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of…

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such…

Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental…

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make…

In the vision and language navigation task, the agent may encounter ambiguous situations that are hard to interpret by just relying on visual information and natural language instructions. We propose an interactive learning framework to…