Metraipolis › archive › dc_f4e58ec6b4f5
Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals — arXiv:2608.21610
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21610
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:38:48.061Z
- SHA-256 of the archived text
0a355982a89903647c194707d7f31f357a4b50c963caf87d57aaf4a21601021d- Stable URL of this page
https://metraipolis.com/documento/dc_f4e58ec6b4f5
How to cite
Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals — arXiv:2608.21610 — arXiv (en), https://arxiv.org/abs/2608.21610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4e58ec6b4f5 (Metraipolis archive dc_f4e58ec6b4f5, sha256 0a355982a89903647c194707d7f31f357a4b50c963caf87d57aaf4a21601021d)
BibTeX
@misc{dcf4e58ec6b4f5,
title = {Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals — arXiv:2608.21610},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21610},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4e58ec6b4f5; sha256 0a355982a89903647c194707d7f31f357a4b50c963caf87d57aaf4a21601021d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, discarding the hierarchical structure of the source. We introduce Semantic Compression Trees (SCT), a hierarchical index in which each node stores only its semantic residual -- the information it adds beyond its parent -- and retrieval proceeds by progressive descent from the root, so that per-query cost is governed by tree depth rather than collection size. We evaluate on QASPER (50 papers, 173 questions) under two protocols differing only in whether the benchmark supplies the relevant document, with bootstrap confidence intervals and paired significance tests throughout. The results are mixed and we report them as such. When the document is given, SCT with a zero-LLM extractive compressor matches dense retrieval on answer quality (0.274 vs. 0.277 F1, $p = 0.37$) using 30% fewer context tokens and no LLM calls to build the index, and residual storage beats storing full summaries at each node (0.274 vs. 0.205, $p < 0.001$). Increasing the collection fifty-fold multiplies flat retrieval's per-query scoring work by 48.9x and SCT's by 6.4x. Progressive descent itself is not supported. Retrieving the same residuals without the tree performs identically when the document is given ($p = 0.27$), and descent is substantially worse when the system must select the document (0.122 vs. 0.165, $p < 0.001$). Routing accuracy localises the cause: descent selects the correct paper 20.2% of the time against 39.3% for flat retrieval, because that choice is made from the root residual, the most compressed node in the tree. We conclude that the residual representation is worth keeping and top-down routing is not. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.21610 — 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 2026-10-18T07:37:52.654Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).