Metraipolis › archive › dc_26543ef23655

SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics — arXiv:2610.06513

Source
arXiv
Original
https://arxiv.org/abs/2610.06513
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:34.304Z
SHA-256 of the archived text
319f3fe4538f0a66da5c8e2214ccc5862003fdf2c694384222dbf2e673112720
Stable URL of this page
https://metraipolis.com/documento/dc_26543ef23655

How to cite

SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics — arXiv:2610.06513 — arXiv, https://arxiv.org/abs/2610.06513 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26543ef23655 (Metraipolis archive dc_26543ef23655, sha256 319f3fe4538f0a66da5c8e2214ccc5862003fdf2c694384222dbf2e673112720)
BibTeX
@misc{dc26543ef23655,
  title = {SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics — arXiv:2610.06513},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06513},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26543ef23655; sha256 319f3fe4538f0a66da5c8e2214ccc5862003fdf2c694384222dbf2e673112720},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06513. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is done by the perplexity. Diffusion and flow-based language models can only provide a likelihood bound, whose tightness differs between model families. Sample-based substitutes such as generative perplexity with entropy do not consider the distribution fit. We propose SOL, a distance between text distributions. Each sequence is represented by the empirical measure of its hidden states under a fixed transformer and the distributions of these measures are compared by the double sliced Wasserstein distance. We prove that SOL is a metric if the transformer is injective. Experiments show that SOL detects distributional failures, recovers expected model trends, and provides stable sample-based estimates. We put forward SOL to fill the gap in the current evaluation protocol used for non auto-regressive models. As a first step we use SOL to re-evaluate a variety of models trained on OpenWebText.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.06513 — 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 2026-10-06T05:24:20.374Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).