Related papers: Model Transformations for Ranking Functions and To…

Qualitative relationships illustrate how changing one property (e.g., moving velocity) affects another (e.g., kinetic energy) and constitutes a considerable portion of textual knowledge. Current approaches use either semantic parsers to…

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…

I propose a framework for an agent to change its probabilistic beliefs when a new piece of propositional information $\alpha$ is observed. Traditionally, belief change occurs by either a revision process or by an update process, depending…

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…

In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large…

While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household…

Transformer-based large language models (LLMs) have demonstrated strong reasoning abilities across diverse fields, from solving programming challenges to competing in strategy-intensive games such as chess. Prior work has shown that LLMs…

Adaptive models of opinion formation among humans can display a fragmentation transition, where a social network breaks into disconnected components. Here, we investigate this transition in a class of models with arbitrary number of…

Word order, an essential property of natural languages, is injected in Transformer-based neural language models using position encoding. However, recent experiments have shown that explicit position encoding is not always useful, since some…

World models have been recently proposed as sandbox environments in which AI agents can be trained and evaluated before deployment. While realistic world models often have high computational demands, this can often be alleviated by…

Participants in political discourse employ rhetorical strategies -- such as hedging, attributions, or denials -- to display varying degrees of belief commitments to claims proposed by themselves or others. Traditionally, political…

Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these…

Logical reasoning is central to complex human activities, such as thinking, debating, and planning; it is also a central component of many AI systems as well. In this paper, we investigate the extent to which encoder-only transformer…

State machine formalisms equipped with hierarchy and parallelism allow to compactly model complex system behaviours. Such models can then be transformed into executable code or inputs for model-based testing and verification techniques.…

We consider credibility-limited revision in the framework of belief change for epistemic spaces, permitting inconsistent belief sets and inconsistent beliefs. In this unrestricted setting, the class of credibility-limited revision operators…

The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…

Why do people who disagree about one subject tend to disagree about other subjects as well? In this paper, we introduce a model to explore this phenomenon of "epistemic factionization". Agents attempt to discover the truth about multiple…

Agentic reinforcement learning increasingly relies on experience-driven scaling, yet real-world environments remain non-adaptive, limited in coverage, and difficult to scale. World models offer a potential way to improve learning efficiency…

Despite the fact that beliefs are mental states that cannot be directly observed, humans talk about each others' beliefs on a regular basis, often using rich compositional language to describe what others think and know. What explains this…

In action domains where agents may have erroneous beliefs, reasoning about the effects of actions involves reasoning about belief change. In this paper, we use a transition system approach to reason about the evolution of an agents beliefs…