T-REX: Table -- Refute or Entail eXplainer
It addresses the challenge of making advanced table fact-checking accessible to non-experts, which is an incremental improvement over existing methods.
The paper tackles the problem of verifying textual claims against tabular data by introducing T-REX, an interactive tool that uses instruction-tuned reasoning LLMs to provide accurate and transparent fact-checking for non-experts, making it openly available online.
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.