MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lagos, Maximiliano Hormazábal, Sáez, Álvaro Bueno, Cerezo-Costas, Héctor, Doval, Pedro Alonso, Vesteiro, Jorge Alcalde
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909692688596992
author Lagos, Maximiliano Hormazábal
Sáez, Álvaro Bueno
Cerezo-Costas, Héctor
Doval, Pedro Alonso
Vesteiro, Jorge Alcalde
author_facet Lagos, Maximiliano Hormazábal
Sáez, Álvaro Bueno
Cerezo-Costas, Héctor
Doval, Pedro Alonso
Vesteiro, Jorge Alcalde
contents 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 obtains answers to the questions by implementing Python code generation with LLMs that is used to filter and process the table. This solution evolves from the MRT implementation for the Semeval 2025 related task. The process consists of multiple steps: analyzing and understanding the content of the table, selecting the useful columns, generating instructions in natural language, translating these instructions to code, running it, and handling potential errors or exceptions. These steps use open-source LLMs and fine-grained optimized prompts for each step. With this approach, we achieved an accuracy score of 85\% in the task.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
Lagos, Maximiliano Hormazábal
Sáez, Álvaro Bueno
Cerezo-Costas, Héctor
Doval, Pedro Alonso
Vesteiro, Jorge Alcalde
Computation and Language
Artificial Intelligence
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 obtains answers to the questions by implementing Python code generation with LLMs that is used to filter and process the table. This solution evolves from the MRT implementation for the Semeval 2025 related task. The process consists of multiple steps: analyzing and understanding the content of the table, selecting the useful columns, generating instructions in natural language, translating these instructions to code, running it, and handling potential errors or exceptions. These steps use open-source LLMs and fine-grained optimized prompts for each step. With this approach, we achieved an accuracy score of 85\% in the task.
title MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.12981