MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps

2025/05/28 by Maximiliano Hormazábal Lagos, Lagos, Maximiliano Hormazábal, Alex Saez +7 · 2 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2505.22264

openalex publication_date 2025/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper we expose our approach to solve the SemEval 2025 Task 8: Question-Answering over Tabular Data challenge. Our strategy leverages Python code generation with LLMs to interact with the table and get the answer to the questions. The process is composed of multiple steps: understanding the content of the table, generating natural language instructions in the form of steps to follow in order to get the answer, 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 task (step). With this approach, we achieved a score of 70.50% for subtask 1.

Citations

• Phi-4 Technical Report
• Evaluating and Aligning CodeLLMs on Human Preference
• Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering
• TableRAG: Million-Token Table Understanding with Language Models
• Qwen2.5-Coder Technical Report
• Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution
• Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
• TabFact: A Large-scale Dataset for Table-based Fact Verification
• A Comprehensive Exploration on WikiSQL with Table-Aware Word\n Contextualization

Cited by

• MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
• ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

Related

• MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
• Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
• AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering
• ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation
• LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA