Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model
This addresses fact verification for users handling multi-modal data, but it is incremental as it builds on existing benchmarks and methods.
The paper tackled the problem of fact verification using both text and tabular data by introducing a lightweight attention-based model that avoids modality conversion, achieving competitive performance on the FEVEROUS benchmark.
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.