Metraipolis › archive › dc_f626a32303ea
Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits — arXiv:2611.05355
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05355
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:33:44.083Z
- SHA-256 of the archived text
3273a57886cc3a0aa6d0a500c6810fca0d7a05464013b6fc5737d42db6c7d20f- Stable URL of this page
https://metraipolis.com/documento/dc_f626a32303ea
How to cite
Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits — arXiv:2611.05355 — arXiv (en), https://arxiv.org/abs/2611.05355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f626a32303ea (Metraipolis archive dc_f626a32303ea, sha256 3273a57886cc3a0aa6d0a500c6810fca0d7a05464013b6fc5737d42db6c7d20f)
BibTeX
@misc{dcf626a32303ea,
title = {Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits — arXiv:2611.05355},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05355},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f626a32303ea; sha256 3273a57886cc3a0aa6d0a500c6810fca0d7a05464013b6fc5737d42db6c7d20f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When a language model answers, we can usually only estimate why. We build a transformer in which every step is a Born measurement - attention $|\langle q|k\rangle|^4$ normalised over each row, a measured product in place of the feed-forward nonlinearity, and a Born readout. With its denominators held at their values for the input, each class probability is a polynomial in the word amplitudes, so its integrated-gradient evidence is computed by a finite quadrature with no quadrature error: the words' contributions sum to the class probability above its no-information share, to $10^{-11}$ or better. On e-SNLI natural language inference, with about 98k parameters outside the embedding, the model reaches $76.98 \pm 0.17$% test accuracy, level with a softmax transformer of the same size ($76.62 \pm 0.36$%). Deleting the word its evidence ranks first changes the answer in 45% of test pairs, out of the 53% any single deletion can change, against 32% for the softmax model explained the same way and 40% by its attention x gradient. Attention can look more like the words annotators highlighted, yet accounts for the answer less well: deleting the word it ranks first changes the Born Transformer's answer in 32% of pairs. The same weights compile exactly to optoelectronic optics and to qubits, and a coherent attention layer becomes one circuit equal to the model (852 CNOTs on 23 qubits). On IBM's ibm_kingston, reading only the attention overlaps by Hadamard tests, the device gave the model's answers on two short test pairs and kept or changed them under deletion as the model does; the evidence itself did not yet survive the device, and we work out the shots and calibration that measuring it on hardware would need.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Quantum Physics (quant-ph) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Optics (physics.optics).
Pagina del lavoro: https://arxiv.org/abs/2611.05355 — 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 2026-11-04T12:27:02.077Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).