Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification

Abstract--This paper investigates fake news detection as a downstream evaluation of Transformer representations, bench-marking encoder-only and decoder-only pre-trained models (BERT, GPT -2, Transformer-XL) as frozen embedders paired with lightweight classifiers. Through controlled preprocessing comparing pooling versus padding and neural versus linear heads, results demonstrate that contextual self-attention encodings consistently transfer effectively. BERT embeddings combined with logistic regression outperform neural baselines on LIAR dataset splits, while analyses of sequence length and aggregation reveal robustness to truncation and advantages from simple max or average pooling. In the pre-digital era, the dissemination of information to mass audiences was predominantly controlled by established publishing organizations and media conglomerates that maintained editorial standards and fact-checking processes. The advent of the Internet and the subsequent proliferation of social media platforms have fundamentally transformed this landscape, democratizing information sharing by enabling any individual to broadcast news and content to global audiences with unprecedented speed and scale [6]. While this democratization has fostered greater accessibility to diverse perspectives, it has simultaneously introduced significant challenges to ensuring the validity, authenticity, and reliability of the information being circulated [8].