T-REX: Table -- Refute or Entail eXplainer

TL;DR

T-REX is an interactive tool that leverages advanced instruction-tuned LLMs to verify claims against multilingual tables, making table fact-checking accessible and transparent for non-experts.

Contribution

It introduces the first live, multimodal, multilingual fact-checking system for tables using state-of-the-art reasoning LLMs, enhancing accessibility and transparency.

Findings

First live, interactive table claim verification tool.

Supports multilingual and multimodal tables.

Empowers non-experts with advanced fact-checking capabilities.

Abstract

Verifying textual claims against structured tabular data is a critical yet challenging task in Natural Language Processing with broad real-world impact. While recent advances in Large Language Models (LLMs) have enabled significant progress in table fact-checking, current solutions remain inaccessible to non-experts. We introduce T-REX (T-REX: Table -- Refute or Entail eXplainer), the first live, interactive tool for claim verification over multimodal, multilingual tables using state-of-the-art instruction-tuned reasoning LLMs. Designed for accuracy and transparency, T-REX empowers non-experts by providing access to advanced fact-checking technology. The system is openly available online.