SLATE'26

Thursday, 25^th June | Friday, 26^th June | Keynotes

25^th June

Papers/Events	Authors	Time
Registration		13:00
Welcome Session		13:30
Keynote		14:00
AMALIA: An Open Source Large Language Model for European Portuguese	João Magalhães
Session I		15:00
Optimising Retrieval for Linguistic Question-Answering in European Portuguese: A Benchmark on Ciberdúvidas da Língua Portuguesa	Pedro Moura, Inês Gama, Fernando Batista, and António Lopes
Evaluating the Prosodic Diversity of TTS Models for L2 Prosody Assessment	Mariana Julião, Alberto Abad, and Helena Moniz
Cross-Language Text Readability Assessment: Leveraging Multilingual Models for Improved Performance in CEFR-Level Classification	Eugénio Ribeiro and Jorge Baptista
Coffee Break		16:15
Session II		16:40
OntoExpand: SPARQL-Based Ontology Expansion and Reasoning	Vitor Lelis N. Leite and José Carlos L. Ramalho
An OWL/RDF Ontology for Declarative User Interface Generation	Daniel Theisges da Costa, Júlio Costa, Paulo Jorge Teixeira Matos, Ramon Gallinad Corti, Ramon Vilanova i Arbos, and Maria João Tinoco Varanda Pereira
A Silent Multi-Agent Recommendation Engine with Graph-Augmented Memory for Immersive B2B E-Commerce	Davi Silva Eleuterio, Pedro Filipe Oliveira, and Paulo Matos
Deductive Databases and Logic Programming	Dietmar Seipel and Salvador Abreu
Conference Dinner		19:30

26^th June

Papers/Events	Authors	Time
Keynote		09:00
Æon: A Programming Language with Guardrails	Alcides Fonseca
Session III		10:00
Lazarus: Where Compilers Meet Education	Rui Gonçalves, Pedro Rangel Henriques, and José Carlos Ramalho
Out of the Loop No More: Online Abstract Debugging with Loop Stepping	João Alvim, Maarten Steevens, and Christophe Scholliers
RI: A DSL for Software Development Project Continuous Configuration	Cássio Ritse Machado Dos Santos Silva, Maria João Varanda Pereira, Paulo Alexandre Vara Alves, and Gustavo Jansen de Souza Santos
Coffee Break		11:15
Session IV		11:40
Coordinating Multi‑Assistant Interaction in Smart Homes: A Front‑End Delegation Approach	Pedro Carneiro, Inês Águia, Nuno Almeida, and António Teixeira
Automating the Classification of Smart Tourism Solutions with LLMs: A Taxonomy-Driven Approach	Diogo Cosme, Fernando Batista, António Galvão, Fernando Brito e Abreu, and Mariana Casal-Ribeiro
From Natural Language to Structured Queries: An LLM-Powered Chatbot for a Smart Tourism Observatory	Rodrigo Bravo Simões, Adriano Lopes, and Fernando Brito e Abreu
Lunch		13:00
Session V		14:30
Assessing LLMs for Culturally Sensitive Communication in European Portuguese	Alice Vieira, Raquel Amaro, and Lyndon Nixon
BERT-based Classification of Cross-Linguistic MCQs According to the Bloom Taxonomy	João Francisco Botas, Ana Rita Peixoto, and Eugénio Ribeiro
A Topic-Word Graph for Topic Modeling Visualization	Ana Rita Peixoto
Inter-sentential Relations in Enhanced Lexicalized Meaning Representation (E-LMR)	Jorge Baptista
Coffee Break		16:10
Session VI		16:30
Developing an AI-Based Application for Linguistic Analysis of Deaf Learners' L2 Writing	Aryane Santos Nogueira and Ana Célia Ribeiro Bizigato Portes
Polarizations in Static Word Embeddings: Investigating Bias in Marginalized Dialects of Portuguese	Raimundo Juracy Campos Ferro Junior, Eugénio Ribeiro, and Leonardo Sampaio Rocha
Gender Bias Evaluation in English-Portuguese Automated Translation Outputs	Xiaolan Xu and Sara Mendes
Cost-Effective Hate Speech Detection in Portuguese Using Lightweight LLMs	Mauro Cardoso, Eugénio Ribeiro, and Fernando Batista
Closing Session		18:10

Æon: A Programming Language with Guardrails

Alcides Fonseca

LASIGE, Faculdade de Ciências da Universidade de Lisboa

Abstract

Program Synthesis is the dream of every developer. You specify what you want to write, and the computer writes the code for you. This specification can take several shapes: the signature (types) of a function, its documentation, or some input-output examples. Æon is a programming language that supports different algorithms: LLMs, Genetic Programming and SMT Solvers. In particular, Æon takes advantage of an advanced type system (Liquid Types) to validate whether the generated code is correct. The talk will cover how to make the best out of these techniques, and show examples that are more suitable for some techniques than others.

Short Bio

Alcides Fonseca is an Associate Professor at the Faculty of Sciences of the University of Lisbon. Alcides has a PhD, a MSc and a BSc from the University of Coimbra. His research covers the intersection of Machine Learning and Programming Languages, having build several programming languages and related tools, namely with liquid types and genetic programming. Apart from research, Alcides has been a consultant for several startups (Dragonboat, Genomed, SmashTech, Sentilant, Spero, Burocratik) and multinational companies (Ogilvy & Mather).

AMALIA: An Open Source Large Language Model for European Portuguese

João Magalhães

NOVA LINCS, Universidade NOVA de Lisboa

Abstract

Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresented in both training data and native evaluation, with machine-translated benchmarks likely missing the variant's linguistic and cultural nuances. We introduce AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages. To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias. Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations, supporting the case for targeted training and native benchmarking for European Portuguese.

Short Bio

Prof. João Miguel da Costa Magalhães is a Full Professor in the Department of Computer Science at Universidade NOVA de Lisboa and a senior researcher at NOVA LINCS. He serves as co-Director of the CMU Portugal Program and leads the NOVA LINCS Multimodal Systems Group. He holds a PhD from Imperial College London (2008) and his research focuses on vision-language models, multimodal learning, and AI systems for semantic multimedia. João has coordinated and contributed to international projects with R&D leading partners BBC, Amazon and Google. He is the Technical Program Committee Chair of the 2026 ACM International Conference in Multimedia and in 2022 was the General Chair.

Organization

25th June

26th June

Æon: A Programming Language with Guardrails

Alcides Fonseca

LASIGE, Faculdade de Ciências da Universidade de Lisboa

Abstract

Short Bio

AMALIA: An Open Source Large Language Model for European Portuguese

João Magalhães

NOVA LINCS, Universidade NOVA de Lisboa

Abstract

Short Bio

25^th June

26^th June