Pith. sign in

REVIEW 1 cited by

Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.13297 v2 pith:2EDXAJ5J submitted 2023-05-22 cs.CL

classification cs.CL
keywords attentionfeed-forwardblockdesignassumptionsffnsmodelsnetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper investigates the key role of Feed-Forward Networks (FFNs) in transformer models by utilizing the Parallel Attention and Feed-Forward Net Design (PAF) architecture, and comparing it to their Series Attention and Feed-Forward Net Design (SAF) counterparts. Central to the effectiveness of PAF are two main assumptions regarding the FFN block and the attention block within a layer: 1) the primary function of the FFN block is to maintain isotropy among token embeddings and prevent their degeneration, and 2) the residual norm computed in the attention block is substantially smaller than the input token embedding norm. To empirically validate these assumptions, we train PAF variants of two large language models (RoBERTa-large and bert-large-uncased). Our results demonstrate that both assumptions hold true in the PAF design. This study contributes to a deeper understanding of the roles and interactions between FFNs and self-attention mechanisms in transformer architectures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning

    cs.AI 2025-02 conditional novelty 6.0 of 10

    POI-Enhancer uses LLM-generated text features and attention-based fusion to improve POI embeddings from six classic models, gaining consistent accuracy on three real-world mobility datasets.

Pith tools