Pith. sign in

REVIEW 2 cited by

Talking-Heads Attention

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2003.02436 v1 pith:D7VLL33G submitted 2020-03-05 cs.LG cs.NEcs.SDeess.ASstat.ML

Noam Shazeer , Zhenzhong Lan , Youlong Cheng , Nan Ding , Le Hou This is my paper · ORCID
classification cs.LGcs.NEcs.SDeess.ASstat.ML
keywords attentiontalking-headsbetterlanguagetasksacrossadditionaladditionalcomputation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Mosaic shows that a fleet of four heterogeneous user-embedding specialists, trained with redundancy-reduction and composite-label losses, improves downstream recommendation quality at Meta.

  2. LoSA-Net: A Localized and Scale-Adaptive Network for Boundary-Sensitive Prediction of Perineural Invasion in 3D MRI

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A localized, scale-adaptive 3D encoder (TNA+SAFM+CSRA) predicts perineural invasion from contrast-enhanced MRI with AUC 0.7567, outperforming matched CNN and transformer baselines on 168 patients.

Pith tools