Metraipolis › archive › dc_2672ae799c64
Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings — arXiv:2610.41785
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41785
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:12:44.620Z
- SHA-256 of the archived text
55b5a4c5cc8a724c18993f423986f430dd26a5ea82ffa4d5135f172da6b0dbe8- Stable URL of this page
https://metraipolis.com/documento/dc_2672ae799c64
How to cite
Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings — arXiv:2610.41785 — arXiv (en), https://arxiv.org/abs/2610.41785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2672ae799c64 (Metraipolis archive dc_2672ae799c64, sha256 55b5a4c5cc8a724c18993f423986f430dd26a5ea82ffa4d5135f172da6b0dbe8)
BibTeX
@misc{dc2672ae799c64,
title = {Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings — arXiv:2610.41785},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41785},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2672ae799c64; sha256 55b5a4c5cc8a724c18993f423986f430dd26a5ea82ffa4d5135f172da6b0dbe8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based pipelines (ii) depend on expensive task-specific training that does not transfer across domains. We report an empirical finding that bears on both: in Matryoshka Representation Learning (MRL) embeddings, where each leading prefix is itself a usable, coarser vector, prefix length aligns with the coarse-to-fine granularity of gold taxonomies; shuffled- and reverse-dimension controls isolate the alignment to the learned early prefix dimensions. The pattern holds across three architecturally distinct MRL models. To test whether this regularity is usable, we introduce PEEL (Peeling Embeddings to Extract Latent ontologies): a minimal probe over these frozen embeddings, trained once with an order-embedding objective that represents hierarchy as vector containment; a minimum spanning arborescence then decodes taxonomic DAGs. Using only a concept vocabulary (no documents), PEEL recovers taxonomic DAGs with high structural fidelity on two OLLM benchmarks, transferring to a new domain with no target-edge supervision. The end-to-end OLLM pipeline, which jointly discovers concepts and induces structure from document corpora, is reported as a cross-task reference. Pre-trained retrieval embeddings encode a decodable granularity gradient; a minimal probe renders it as explicit parent-child (is-a) structure. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41785 — 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 2026-11-02T07:07:14.204Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).