Go to ACL ARR 2025 February homepageFLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats
Abstract: The table reasoning task aims to answer the question according to the given table. Currently, using Large Language Models (LLMs) is the predominant method for table reasoning. Most existing methods employ a fixed tabular format to represent the table, which could limit the performance since different instances and models suit different tabular formats. We prove the claim through quantitative analysis of experimental results, where different instances and models perform differently using various tabular formats. Building on this discussion, we propose FLEXTAF-Single and FLEXTAF-Vote to enhance table reasoning performance by employing flexible tabular formats. Specifically, (i) FLEXTAF-Single trains a classifier to predict the most suitable tabular format based on the instance and the LLM and utilize the format to reason. (ii) FLEXTAF-Vote integrates the results across different formats. Our experiments on WikiTableQuestions and TabFact bring average improvements of 2.3% and 4.4%, thereby validating the effectiveness of our methods.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: Question Answering
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 3342
Loading