Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
This work provides an incremental analysis for researchers in NLP and misinformation detection by isolating Transformer contributions in deception classification tasks.
The paper tackled fake news detection by evaluating pretrained Transformer embeddings as frozen features with lightweight classifiers, finding that BERT embeddings with logistic regression outperformed neural baselines on the LIAR dataset.
This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking 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. This work positions attention-based token encoders as robust, architecture-centric foundations for veracity tasks, isolating Transformer contributions from classifier complexity.