Misinformation Detection using Large Language Models with Explainability

TL;DR

This paper presents an explainable, efficient misinformation detection pipeline using fine-tuned transformer-based language models like RoBERTa and DistilBERT, with interpretability tools to ensure transparency and trustworthiness.

Contribution

It introduces a two-step fine-tuning strategy for lightweight PLMs and integrates explainability methods, enabling scalable and interpretable misinformation detection without performance loss.

Findings

DistilBERT achieves comparable accuracy to RoBERTa with less computational cost.

The proposed pipeline provides faithful local and global explanations.

Lightweight PLMs can effectively detect misinformation while being resource-efficient.

Abstract

The rapid spread of misinformation on online platforms undermines trust among individuals and hinders informed decision making. This paper shows an explainable and computationally efficient pipeline to detect misinformation using transformer-based pretrained language models (PLMs). We optimize both RoBERTa and DistilBERT using a two-step strategy: first, we freeze the backbone and train only the classification head; then, we progressively unfreeze the backbone layers while applying layer-wise learning rate decay. On two real-world benchmark datasets, COVID Fake News and FakeNewsNet GossipCop, we test the proposed approach with a unified protocol of preprocessing and stratified splits. To ensure transparency, we integrate the Local Interpretable Model-Agnostic Explanations (LIME) at the token level to present token-level rationales and SHapley Additive exPlanations (SHAP) at the global feature attribution level. It demonstrates that DistilBERT achieves accuracy comparable to RoBERTa while requiring significantly less computational resources. This work makes two key contributions: (1) it quantitatively shows that a lightweight PLM can maintain task performance while substantially reducing computational cost, and (2) it presents an explainable pipeline that retrieves faithful local and global justifications without compromising performance. The results suggest that PLMs combined with principled fine-tuning and interpretability can be an effective framework for scalable, trustworthy misinformation detection.