# Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model

arXiv: https://arxiv.org/abs/2403.17361 · HTML: https://mlsanity.com/paper/2403.17361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [INFOTABS: Inference on Tables as Semi-structured Data](https://mlsanity.com/paper/2005.06117/) (2020)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)](https://mlsanity.com/paper/2105.13995/) (2021)
- [A Multi-Level Attention Model for Evidence-Based Fact Checking](https://mlsanity.com/paper/2106.00950/) (2021)
- [Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verification](https://mlsanity.com/paper/2109.12349/) (2021)

## Abstract (arXiv)

FEVEROUS is a benchmark and research initiative focused on fact extraction and verification tasks involving unstructured text and structured tabular data. In FEVEROUS, existing works often rely on extensive preprocessing and utilize rule-based transformations of data, leading to potential context loss or misleading encodings. This paper introduces a simple yet powerful model that nullifies the need for modality conversion, thereby preserving the original evidence's context. By leveraging pre-trained models on diverse text and tabular datasets and by incorporating a lightweight attention-based mechanism, our approach efficiently exploits latent connections between different data types, thereby yielding comprehensive and reliable verdict predictions. The model's modular structure adeptly manages multi-modal information, ensuring the integrity and authenticity of the original evidence are uncompromised. Comparative analyses reveal that our approach exhibits competitive performance, aligning itself closely with top-tier models on the FEVEROUS benchmark.