EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Margin- and Vocabulary-Aware Adaptive Retrieval for Industrial Technical Question Answering: A Controlled Pilot

Lily Qian, Caroline Wu

Journal of Computing and Electronic Information Management · 05.11.2026 · 23 (2) · 1-8

DOI: 10.54097/bhr7y923 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 05.11.2026. Verfasst von Lily Qian und 1 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient industrial question answering requires reliable evidence retrieval despite document-specific terminology and spelling variation. We study confidence-gated dual retrieval (CGDR), which uses the normalized BM25 top-two margin to decide whether to invoke a complementary character n-gram index. On 80 held-out synthetic questions generated from a published review of domain-adapted industrial language models, the margin-only selector obtains 92.5% Recall@1 with 17.5% complementary-index calls. Yet additional spelling edits reveal substantial brittleness: Recall@1 falls to 38.75% for character deletion or transposition. We therefore introduce an out-of-vocabulary (OOV)-aware gate, combining rank ambiguity with lexical coverage of the indexed corpus. Its rule is fitted on separate development pages and their deterministic perturbations under a 55% development-stage call budget. On held-out deletion and transposition edits, the revised gate increases Recall@1 to 60.0% in each condition, compared with 38.75% for the margin-only gate, while requiring the character index on 60% of these requests. On unmodified questions, it returns 91.25% Recall@1 at a 21.25% call rate. Because this gate was designed after the margin-only analysis, its held-out gains are reported as exploratory. The improvements are measured on 80 underlying held-out queries with dependent synthetic transformations, not on naturally authored questions or a production system. Passage-level evaluation, sentence-extraction checks, matched-budget controls, and source-auditable code characterize the robustness–cost trade-off; no generative language model is evaluated.

Zitieren

APA

Qian, L., & Wu, C. (2026). Margin- and Vocabulary-Aware Adaptive Retrieval for Industrial Technical Question Answering: A Controlled Pilot. Journal of Computing and Electronic Information Management, 23(2), 1-8. https://doi.org/10.54097/bhr7y923

Vancouver

Qian L, Wu C. Margin- and Vocabulary-Aware Adaptive Retrieval for Industrial Technical Question Answering: A Controlled Pilot. Journal of Computing and Electronic Information Management. 2026;23(2):1-8. doi:10.54097/bhr7y923

BibTeX
@article{Qian2026,
  author = {Qian, Lily and Wu, Caroline},
  title = {Margin- and Vocabulary-Aware Adaptive Retrieval for Industrial Technical Question Answering: A Controlled Pilot},
  journal = {Journal of Computing and Electronic Information Management},
  year = {2026},
  volume = {23},
  number = {2},
  pages = {1--8},
  doi = {10.54097/bhr7y923}
}
Kostenlos starten →