9:15-9:30 – Welcome
9:30-10:30 – Keynote Speaker: Zied Bouraoui
Learning Semantic Concept Embedding from Langage Models
10:30-11:00 – Coffee break
11:00-12:30 – Session 1 (20 mins presentation + 10 mins discussion)
- Transformer-based hierarchical attention models for solving analogy puzzles between longer, lexically richer and semantically more diverse sentences
- Learning Analogies between Classes to Create Counterfactual Explanations
- Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
12:30-14:30 – Lunch break
14:30-15:30 – Keynote: Emiliano Lorini
A Novel View of Analogical Proportion between Formulas
15:30-16:00 – Coffee break
16:00-17:30 – Session 2 (20 mins presentation + 10 mins discussion)
- Towards a unified framework of numerical analogies: Open questions and perspectives
- Testing proportional sentence analogies on SATS: from vector offsets to conditional generation
- Probing Large Language Models to Perform Analogical Transformation
