mlsanityData to 14 Oct 2026

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

arXiv 2507.12981 ↗First posted 17 Jul 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents our approach for the IberLEF 2025 Task PRESTA: Preguntas y Respuestas sobre Tablas en Espa~nol (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

13 of 19 references.

References · 13

  1. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  2. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  3. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  4. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  5. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  6. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
  7. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  8. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 41
  9. 2023Rethinking Tabular Data Understanding with Large Language Modelscited by 36
  10. 2022OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answeringcited by 29
  11. 2022TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Datacited by 19
  12. 2024Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuningcited by 6
1 more
  1. 2025MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Stepscited by 2

Built on by

Not cited yet.