Metraipolis › archive › dc_cabd78f27293

Annotated Surrogate Retrieval for Polish Statutory Law — arXiv:2608.30929

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30929
License (as archived)
CC0-1.0
Archived
2026-10-17T08:07:50.487Z
SHA-256 of the archived text
a29f07e479ba72c0b88ae8f0e69518f7a7415c673167f25f5bdf5bcaa9ccb5a2
Stable URL of this page
https://metraipolis.com/documento/dc_cabd78f27293

How to cite

Annotated Surrogate Retrieval for Polish Statutory Law — arXiv:2608.30929 — arXiv (en), https://arxiv.org/abs/2608.30929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cabd78f27293 (Metraipolis archive dc_cabd78f27293, sha256 a29f07e479ba72c0b88ae8f0e69518f7a7415c673167f25f5bdf5bcaa9ccb5a2)
BibTeX
@misc{dccabd78f27293,
  title = {Annotated Surrogate Retrieval for Polish Statutory Law — arXiv:2608.30929},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30929},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cabd78f27293; sha256 a29f07e479ba72c0b88ae8f0e69518f7a7415c673167f25f5bdf5bcaa9ccb5a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a family of retrieval methods for Polish statutory law built on document surrogates: language-model annotations attached to statutory articles at index time. Three designs occupy different points on the cost-quality frontier. ASCR is a surrogate cascade with reranking; ASCR-H fuses a dense list into that cascade; and DTF replaces both language-model stages with three lexical and dense retrievers, weighted reciprocal rank fusion, and a deterministic re-scoring prior, using no model call before generation. We evaluate all three against fourteen lexical, dense, fused and ablated baselines plus four controls, on 300 questions from the 2024 and 2025 Polish bar and legal counsel entrance examinations (264 with their reference article in the corpus), over 82,508 articles from 1,133 acts. On paired McNemar tests, ASCR-H places the reference provision at rank one significantly more often than every other non-oracle configuration except one of its own ablations (eighteen of twenty comparisons significant in its favour at p < 0.005), reaching 72.3% against 61.7% for BM25 and 52.3% for dense retrieval. The advantage is concentrated at the head and does not survive depth: it is significant at cutoffs of one and five, disappears by ten, and by twenty DTF leads on point estimate (86.0% versus 84.5%) at one ninth the latency and less than half the cost. Ablation attributes 27.6 points of rank-one accuracy to the reranking stage alone. We further report that the ranking advantage does not extend to citation accuracy, where DTF matches the oracle ceiling, and three negative results on lemmatisation, pseudo-relevance feedback and query rewriting. Surrogate annotation covers 27.0% of the corpus but every reference provision in the benchmark, an asymmetry we disclose and discuss. Benchmark, per-question outputs and paired significance tests are publicly available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.30929 — 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 2026-10-17T07:47:52.870Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).