Adaptive Retrieval and Evidence Calibration for Reliable Retrieval-Augmented Generation
Computer Life · 13.11.2026 · 15 (2) · 33-39
DOI: 10.54097/arjehm36 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Life, online erschienen am 13.11.2026. Verfasst von Clara N. Whitmore. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Retrieval-augmented generation (RAG) can expose a response to incorrect evidence when a retrieved source is plausible but mismatched. This paper presents ACRE, a compact pipeline that couples query-dependent reranking depth, source-evidence confidence estimation, and a selective output decision. A BM25 candidate list is augmented with lexical similarity signals; logistic confidence models select one, three, or five candidates and determine whether a verbatim, source-attributed answer should be issued. We evaluate on 300 authentic news reports and 50 out-of-index reports from the Lee text corpora, using 1,400 reproducibly derived source-identification queries. On the 280-query held-out split, adaptive retrieval matches the BM25 top-1 source accuracy of 77.86% while requiring only 1.73 candidates per query in the assigned reranking depth, versus five for the fixed-depth alternative. With the development-selected abstention threshold, the system responds to 80.36% of test queries at 91.11% accepted-source accuracy; its expected calibration error is 0.039. The results demonstrate an economical approach to coupling retrieval efficiency with calibrated source attribution in an explicitly extractive RAG setting.
Zitieren
APA
Whitmore, C. N. (2026). Adaptive Retrieval and Evidence Calibration for Reliable Retrieval-Augmented Generation. Computer Life, 15(2), 33-39. https://doi.org/10.54097/arjehm36
Vancouver
Whitmore CN. Adaptive Retrieval and Evidence Calibration for Reliable Retrieval-Augmented Generation. Computer Life. 2026;15(2):33-39. doi:10.54097/arjehm36
BibTeX
@article{Whitmore2026,
author = {Whitmore, Clara N.},
title = {Adaptive Retrieval and Evidence Calibration for Reliable Retrieval-Augmented Generation},
journal = {Computer Life},
year = {2026},
volume = {15},
number = {2},
pages = {33--39},
doi = {10.54097/arjehm36}
}
EUVIMED