Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization

Abstract:Compressed short-text generators can fail in two different places: the codec may discard information before generation starts, or the latent generator may produce weak codes. Without separating these failure modes, researchers can spend compute improving the wrong component. We study this problem in a controlled 64-to-16 TinyStories case study built from a hierarchical VQ-VAE-2 codec and a masked discrete diffusion generator (MDLM). We use a staged validation protocol that separates codec reconstruction fidelity, latent generation quality, and auxiliary latent diagnostics under one shared external GPT-2 scorer, while reporting complementary semantic metrics for the geometry study. In the tested configuration, codec reconstruction alone raises median external perplexity from 15.17 to 27.36 (+80.4%) and p95 from 25.10 to 98.91 (+294.1%), showing that the dominant quality loss appears before latent generation begins. Under the same scorer, code-space MDLM remains materially stronger than token-space diffusion, reducing mean, median, and p95 by 32.9%, 30.9%, and 36.6%, respectively. Geometry-aware regularization improves local latent proxies but does not improve decoded-text metrics in the available runs. The contribution is methodological rather than algorithmic: the paper presents a reusable staged diagnosis for one concrete pipeline and shows that, in this setting, codec fidelity rather than latent denoising sets the practical quality ceiling.

8 pages, 3 figures, 14 tables. Published in the Proceedings of FRUCT'39

Computation and Language (cs.CL); Machine Learning (cs.LG)

arXiv:2607.24176 [cs.CL]

(or arXiv:2607.24176v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.24176 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

Proceedings of the 39th Conference of the Open Innovations Association FRUCT (FRUCT'39), 2026, pp. 69-76

https://doi.org/10.23919/FRUCT70069.2026.11506553 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.