Metraipolis › archive › dc_69644ea3c800
Conic Certification of Transformer Attention — arXiv:2611.00585
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00585
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:05:19.886Z
- SHA-256 of the archived text
a454ad716c1a7a2348fb19b39ee2ba8905210db8b6cd1f03ea19507ed5f8d5b1- Stable URL of this page
https://metraipolis.com/documento/dc_69644ea3c800
How to cite
Conic Certification of Transformer Attention — arXiv:2611.00585 — arXiv (en), https://arxiv.org/abs/2611.00585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69644ea3c800 (Metraipolis archive dc_69644ea3c800, sha256 a454ad716c1a7a2348fb19b39ee2ba8905210db8b6cd1f03ea19507ed5f8d5b1)
BibTeX
@misc{dc69644ea3c800,
title = {Conic Certification of Transformer Attention — arXiv:2611.00585},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00585},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69644ea3c800; sha256 a454ad716c1a7a2348fb19b39ee2ba8905210db8b6cd1f03ea19507ed5f8d5b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Attention is the computational core of large language models, yet the verifiers that bound how far an attention head's output can move under input perturbations give no guarantee on how loose their bounds are. A weak certificate therefore cannot be told apart from a fragile model. We develop a conic programming theory of attention certification that supplies this guarantee. We prove that the difficulty lies not in the softmax but in the bilinear interaction of a varying query with the keys. This interaction makes certification NP-hard over boxes and inapproximable once the attention logits can move by a constant amount. A fixed query or listed token substitutions, by contrast, make the exact worst case efficiently computable. An exponential cone moment relaxation then certifies a head with an error bounded quadratically in the perturbation radius by computable quantities, an order that cannot be improved. We also show that relaxations that treat a network one operation at a time, linear bound propagation among them, pay on second-order terms a sum of per-operation maxima instead of one coupled maximum. Computational results on GPT-2 indicate that the theory carries over to a trained model. Against exact worst cases with the query fixed, the certificate attains the predicted second-order accuracy. It is tighter than linear bound propagation on every head, and the looseness of bound propagation tracks the predicted per-operation excess. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2611.00585 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:59:45.955Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).