These tutorials will provide an introduction and overview of the automatic metaphor processing field. First, we will discuss the influence of various metaphor theories on the creation of annotated resources and models. Then, we will particularly focus on recent directions opened by LLMs for metaphor interpretation in multilingual and multimodal settings. Two types of audience may benefit from this tutorial: researchers in the humanities and computational social sciences interested in automatic or semi automatic metaphor analysis, and NLP researchers interested in understanding metaphor processing and improving metaphor modeling.

Introduction
Through language, images or gestures, we constantly, and often unintentionally, rely on metaphors to express ideas by framing some concepts into others. This core thought mechanism has intrigued researchers for centuries for its role in semantic innovation, fueling poetry and language changes, and as a key rhetorical device in the toolbox of human persuasion techniques, going along well with humor and communication of emotions. Recent years have seen an explosion of research on metaphors in AI/NLP and other various disciplines such as psycho and neuro linguistics, and anthropology.

The last generation of LLMs is opening new perspectives for fine-grained metaphor interpretation and discourse-level metaphor analysis. We are witnessing an acceleration of multilingual and multimodal studies with the development of visual metaphor processing resources and tasks. Moreover, the debated depth of the analogical reasoning abilities of recent models includes metaphor research among the important directions for evaluating and improving the models capacity to generalize from one domain to another.

In this tutorial, we will discuss how NLP tools can support metaphor studies in other disciplines, and how metaphor processing can help us better understand LLMs and their applications. We will adopt a comprehensive perspective, from classic theories of metaphors to the last neural theories. Finally, data will play a central role in the tutorial, as we will present an overview of existing metaphor resources, with a particular emphasis on languages other than English, as well as multilingual and multimodal resources.