5 papers
MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
Maximiliano Hormazábal Lagos, Ãlvaro Bueno Sáez, Héctor Cerezo-Costas +2
This paper presents our approach for the IberLEF 2025 Task PRESTA: Preguntas y Respuestas sobre Tablas en Español (Questions and Answers about Tables in Spanish). Our solution obt…
Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering
Maximiliano Hormazábal Lagos, Héctor Cerezo-Costas, Dimosthenis Karatzas
We introduce EaGERS, a fully training-free and model-agnostic pipeline that (1) generates natural language rationales via a vision language model, (2) grounds these rationales to s…
ExpliCIT-QA: Explainable Code-Based Image Table Question Answering
Maximiliano Hormazábal Lagos, Ãlvaro Bueno Sáez, Pedro Alonso Doval +2
We present ExpliCIT-QA, a system that extends our previous MRT approach for tabular question answering into a multimodal pipeline capable of handling complex table images and provi…
Ask a Local: Detecting Hallucinations With Specialized Model Divergence
Aldan Creo, Héctor Cerezo-Costas, Pedro Alonso-Doval +1
Hallucinations in large language models (LLMs) - instances where models generate plausible but factually incorrect information - present a significant challenge for AI. We introduc…
MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps
Maximiliano Hormazábal Lagos, Ãlvaro Bueno Saez, Héctor Cerezo-Costas +2
In this paper we expose our approach to solve the \textit{SemEval 2025 Task 8: Question-Answering over Tabular Data} challenge. Our strategy leverages Python code generation with L…