Metraipolis › archive › dc_de7d0196abc6

ISBC: Interpretable Sparse Binary Coding of Pretrained Text Embeddings — arXiv:2611.00999

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00999
License (as archived)
CC0-1.0
Archived
2026-11-03T18:36:42.007Z
SHA-256 of the archived text
1f203dd078b51520ea941f420eefe0a50faefc05a7c9a20d49f4e7717b4968c5
Stable URL of this page
https://metraipolis.com/documento/dc_de7d0196abc6

How to cite

ISBC: Interpretable Sparse Binary Coding of Pretrained Text Embeddings — arXiv:2611.00999 — arXiv (en), https://arxiv.org/abs/2611.00999 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de7d0196abc6 (Metraipolis archive dc_de7d0196abc6, sha256 1f203dd078b51520ea941f420eefe0a50faefc05a7c9a20d49f4e7717b4968c5)
BibTeX
@misc{dcde7d0196abc6,
  title = {ISBC: Interpretable Sparse Binary Coding of Pretrained Text Embeddings — arXiv:2611.00999},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00999},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de7d0196abc6; sha256 1f203dd078b51520ea941f420eefe0a50faefc05a7c9a20d49f4e7717b4968c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00999. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained text embeddings encode semantic structure in high-dimensional continuous spaces whose coordinates are difficult to interpret. We introduce Interpretable Sparse Binary Coding (ISBC), which learns a small set of binary dimensions from frozen embeddings without taxonomy labels or downstream outcomes. A trainable encoder and affine decoder combine reconstruction with controls on activity, factor utilization, dependence, and activation uncertainty. Individual bits and their conjunctions select overlapping document groups; complete activation profiles provide finer contexts for conditional comparisons. We evaluate these representations across corpora, backbones, and code configurations through reconstruction, geometry, predictive probes, and document inspection. Empirical cases identify both distinctions within existing categories and shared content across their boundaries. In a mixed-domain corpus, the most frequent profiles predominantly identify source collections, while selected within-source comparisons reveal sentiment and migration contrasts. Selected associations persist in additional documents encoded without refitting. In an engagement application, bits alone improve prediction of log-transformed outcomes over a constant reference, while their combinations identify within-event content contrasts associated with engagement. The results support using binary coordinates and their combinations for empirical interpretation, with complete profiles providing a fine, partly initialization-dependent description rather than a unique discrete taxonomy.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00999 — 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 2026-11-03T18:12:54.466Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).