.png){kind=icon}
.png){kind=icon}
Return
T-REX: Table - Refute or Entail eXplainer
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-06129-4_33.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 (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. Online Demo: https://t-rex.r2.enst.fr Demo (video): https://www.youtube.com/watch?v=HHIxVCOT8X0 Github: https://github.com/TimLukaHorstmann/T-REX
Keywords:
Table Fact-Checking
Large Language Models
Real-Time Fact Verification