A Bethe-Ansatz Source of Early Token Correlations: A marginal-preserving construction for parallel proposals
Parallel token proposals in language-model decoding need a joint law, not merely accurate token marginals. We construct a family of coordinate-Bethe-ansatz laws from the periodic XXZ chain and compare each with its maximum-entropy pairwise projection at identical one- and two-site moments. In the eight-site, three-excitation sector, symmetry makes their entire probability-law difference one-dimensional, determined by a contiguous three-site moment. Along the Bethe branch, this gap varies with anisotropy, changes sign, and vanishes exactly at $Δ=(3+\sqrt{3})/2$, where the eigenstate law becomes exactly pairwise. A nonlinear readout transfers a nonzero gap into the first two token positions...
| Authors | Abraham Chachamovits |
|---|---|
| Primary category | cs.CL |
| Published | 12 October 2026 |
| Last updated at source | 12 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.