Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917111424614400 |
|---|---|
| author | Mamtani, Sumit Bhure, Abhijeet |
| author_facet | Mamtani, Sumit Bhure, Abhijeet |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22977 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification Mamtani, Sumit Bhure, Abhijeet Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2511.22977 |