Metraipolis › archive › dc_de05651bee49
Scout: Scalable Document Extraction via Data Similarity — arXiv:2608.08261
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08261
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:14:22.894Z
- SHA-256 of the archived text
5e23f03b9b6e12f352b9cbbfa6cd1edc65b53ea137b0bad54d328d95e2e1ba19- Stable URL of this page
https://metraipolis.com/documento/dc_de05651bee49
How to cite
Scout: Scalable Document Extraction via Data Similarity — arXiv:2608.08261 — arXiv (en), https://arxiv.org/abs/2608.08261 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de05651bee49 (Metraipolis archive dc_de05651bee49, sha256 5e23f03b9b6e12f352b9cbbfa6cd1edc65b53ea137b0bad54d328d95e2e1ba19)
BibTeX
@misc{dcde05651bee49,
title = {Scout: Scalable Document Extraction via Data Similarity — arXiv:2608.08261},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08261},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de05651bee49; sha256 5e23f03b9b6e12f352b9cbbfa6cd1edc65b53ea137b0bad54d328d95e2e1ba19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08261. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Extracting values from large document collections powers data analysis across many domains. Frontier LLMs extract such values accurately, but processing an entire collection with one is prohibitively costly. Yet this cost is largely avoidable: real-world collections exhibit rich similarity, so for the same query over similar documents, the answer tends to recur in similar locations; an LLM need only read that small span, not the whole document. Prior methods that exploit this similarity fall short: they either assume a rigid document structure, or assume the answer is a set of substrings of the input and use an LLM-generated program to return it directly. Even a frontier agent fails to generate effective programs to directly locate the answer's span, as the search space is large and programs learned from a small sample tend to overfit. We present Scout, a tool that generates accurate and cost-effective programs (that we call rules) to extract data at scale. From a few sampled documents, Scout generates a broad rule set and refines it by selecting a pareto-optimal subset with low cost without sacrificing accuracy. We prove rule refinement is NP-hard and give a greedy solution with a provable approximation guarantee. Scout handles collections that are only partly similar, where similarity holds within clusters of documents. In this setting, a sampling strategy, using no LLM, draws samples from each cluster; and a cascade strategy selects a subset of refined rules, falling back to the unrefined rule set when the selected rules don't contain the answer. Experiments on six real-world datasets show that Scout matches the accuracy of the strongest baseline, a frontier LLM agent that reads each full document, while being 61x to over 1000x cheaper on a collection of 1,000 documents, and is 61% more accurate than the strongest prior program-based approach. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.DB). Categorie arXiv: Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2608.08261 — 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 2026-10-19T09:12:27.035Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).