Metraipolis › archive › dc_ad17f243d89a

Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search — arXiv:2610.12390

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12390
License (as archived)
CC0-1.0
Archived
2026-10-09T06:13:52.945Z
SHA-256 of the archived text
968ded943d9f3b1d52b0ac2f60b398ec44d3e33208ad966e0cbdc9502a193e54
Stable URL of this page
https://metraipolis.com/documento/dc_ad17f243d89a

How to cite

Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search — arXiv:2610.12390 — arXiv (en), https://arxiv.org/abs/2610.12390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad17f243d89a (Metraipolis archive dc_ad17f243d89a, sha256 968ded943d9f3b1d52b0ac2f60b398ec44d3e33208ad966e0cbdc9502a193e54)
BibTeX
@misc{dcad17f243d89a,
  title = {Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search — arXiv:2610.12390},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12390},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad17f243d89a; sha256 968ded943d9f3b1d52b0ac2f60b398ec44d3e33208ad966e0cbdc9502a193e54},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial risk-control systems typically rely on structured-data models for efficient prediction, yet substantial valuable information remains embedded in unstructured long text. Extracting this information through manual feature engineering is labor-intensive, while requiring a large language model (LLM) to process every real-time input may not meet practical deployment requirements. To address this challenge, we propose LLM-BlockFE, an LLM-guided offline feature construction framework that converts long text into executable feature programs, thereby avoiding LLM calls during online inference. LLM-BlockFE constructs feature programs by incrementally appending immutable code blocks and evaluates candidate features using a downstream model. To address the tendency of conventional greedy search to become trapped in suboptimal solutions, our method introduces a block-level rollback mechanism based on depth-calibrated credit allocation and advances multiple independent search trajectories in an interleaved manner, reducing redundant exploration by sharing fixed descriptions of each trajectory's exploration direction. After the search, the resulting programs are frozen and deployed to extract structured features for downstream prediction models. Across two public and two private datasets, LLM-BlockFE achieves absolute AUC improvements of 0.0069 to 0.0358 over the strongest baseline on each dataset in the full-dataset comparison. Post-launch monitoring across five deployed financial risk-control applications shows absolute KS improvements of 0.02 to 1.56 percentage points over the existing manually designed strategy.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.12390 — 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 2026-10-09T05:47:15.586Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).