Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture

TL;DR

This paper introduces a multi-modal fact-checking system using evidence retrieval and Transformer encoders, achieving competitive results in the De-Factify 2 challenge.

Contribution

It presents a novel multi-modal fact-checking architecture combining evidence retrieval, pre-trained models, and Transformer encoders for improved veracity detection.

Findings

Achieved a weighted average score of 0.79 on validation and test sets.

Placed 3rd among 9 participants in the challenge.

Demonstrated effectiveness of cross-modal Transformer models for fact checking.

Abstract

In this paper, we present the Logically submissions to De-Factify 2 challenge (DE-FACTIFY 2023) on the task 1 of Multi-Modal Fact Checking. We describes our submissions to this challenge including explored evidence retrieval and selection techniques, pre-trained cross-modal and unimodal models, and a cross-modal veracity model based on the well established Transformer Encoder (TE) architecture which is heavily relies on the concept of self-attention. Exploratory analysis is also conducted on this Factify 2 data set that uncovers the salient multi-modal patterns and hypothesis motivating the architecture proposed in this work. A series of preliminary experiments were done to investigate and benchmarking different pre-trained embedding models, evidence retrieval settings and thresholds. The final system, a standard two-stage evidence based veracity detection system, yields weighted avg. 0.79 on both val set and final blind test set on the task 1, which achieves 3rd place with a small margin to the top performing system on the leaderboard among 9 participants.