Faithfulness- and Distribution-Aware Text Analytics for Business Intelligence: From Evidence Retrieval to Plain-Language Adaptation
Information · 18.11.2026 · 17 (11) · 1169
DOI: 10.3390/info17111169 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 18.11.2026. Verfasst von Georgios Arampatzis und 1 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Business Intelligence systems increasingly rely on complex unstructured evidence, creating a need to retrieve relevant information while presenting it in an accessible form without obscuring decision-relevant content. This study presents a faithfulness- and distribution-aware evidence-to-insight framework that integrates sparse and dense retrieval, neural reranking, plain-language adaptation, reference-free candidate selection, interpretable source-consistency screening, provenance, and conservative source fallback. The empirical evaluation is deliberately component-wise: SciFact is used to evaluate evidence retrieval, PLABA provides an untouched in-domain evaluation of document-level plain-language adaptation and reliability-aware selection, and SimpleText2024 provides a frozen external-transfer evaluation under dataset and input-structure differences. The framework is termed faithfulness-aware in a restricted operational sense because it screens numerical, negation, and uncertainty consistency and can abstain when predefined requirements are not satisfied; it does not provide comprehensive factuality verification. On SciFact, cross-encoder reranking achieves an MRR of 0.8536, compared with 0.7675 for BM25. On the untouched PLABA test partition, Beam-4 achieves a grouped SARI of 46.595, compared with 46.137 for the frozen reference-free selector. Under frozen transfer to SimpleText2024, Greedy becomes the strongest fixed decoder, achieving a sentence-level SARI of 21.046. These findings show that development-time adaptation and selection preferences should not be assumed to remain stable on unseen or structurally different data. The resulting framework therefore distinguishes a simpler quality-first operating mode from a more conservative reliability-first mode that combines consistency screening, traceable provenance, and source fallback.
Zitieren
APA
Arampatzis, G., & Arampatzis, A. (2026). Faithfulness- and Distribution-Aware Text Analytics for Business Intelligence: From Evidence Retrieval to Plain-Language Adaptation. Information, 17(11), 1169. https://doi.org/10.3390/info17111169
Vancouver
Arampatzis G, Arampatzis A. Faithfulness- and Distribution-Aware Text Analytics for Business Intelligence: From Evidence Retrieval to Plain-Language Adaptation. Information. 2026;17(11):1169. doi:10.3390/info17111169
BibTeX
@article{Arampatzis2026,
author = {Arampatzis, Georgios and Arampatzis, Avi},
title = {Faithfulness- and Distribution-Aware Text Analytics for Business Intelligence: From Evidence Retrieval to Plain-Language Adaptation},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1169},
doi = {10.3390/info17111169}
}
EUVIMED