OSCR

Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering.

Overview

Authors: Tanzila Kehkashan1,2, Maha Abdelhaq3, Muhammad Abdullah2, Sharifah Sakinah Syed Ahmad4, Nor Azman Ismail1, Nikola Ivković5, Adnan Akunzada6
ORCID iDs: Tanzila Kehkashan, Maha Abdelhaq, Muhammad Abdullah, Sharifah Sakinah Syed Ahmad, Adnan Akunzada
  1. Faculty of Computing, Universiti Teknologi Malaysia, 81310 Johor Bahru, Malaysia
  2. Faculty of Information Technology, University of Lahore, Sargodha, 40100 Pakistan
  3. Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, 11671 Riyadh, Saudi Arabia
  4. Faculty of Artificial Intelligence and Cyber Security, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, Malaysia
  5. Faculty of Organization and Informatics, University of Zagreb, Varaždin, 42000 Croatia
  6. Department of Data and Cybersecurity, University of Doha for Science and Technology, 24449 Doha, Qatar
Institutions: University of Lahore (Pakistan); University of Technology Malaysia (Malaysia); Princess Nourah bint Abdulrahman University (Saudi Arabia); Technical University of Malaysia Malacca (Malaysia); University of Zagreb (Croatia); University of Doha for Science and Technology (Qatar)
Journal: Scientific reports, volume 16, issue 1, article 25351
Dates: received 3 March 2026; accepted 19 May 2026; published online 3 June 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41598-026-54535-8 · PMID 42236773 · PMCID PMC13473467 · OpenAlex W7163350811
Open access: gold, a free copy (OpenAlex)
Status: data only
Categories: methods / tools (subfield)
Methods: Machine learning
Keywords: Answer reranking, Cross-encoder ensemble, Adaptive confidence weighting, Question answering systems, Transformer models, Engineering, Mathematics and computing
Topic: Topic Modeling (Artificial Intelligence, Computer Science), according to OpenAlex
Funding: European Union – NextGenerationEU
Citations: not cited yet (Europe PMC); 37 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Code and data availability statement

The paper has a code and data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41598-026-54535-8.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 7 authors, 7 keywords, 1 funder, 1 references.

Cite

This paper

Kehkashan, T., Abdelhaq, M., Abdullah, M., Ahmad, S. S. S., Ismail, N. A., Ivković, N., & Akunzada, A. (2026). Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering. Scientific reports, 16(1), 25351. https://doi.org/10.1038/s41598-026-54535-8

BibTeX

@article{kehkashan2026adaptive,
author = {Kehkashan, Tanzila and Abdelhaq, Maha and Abdullah, Muhammad and Ahmad, Sharifah Sakinah Syed and Ismail, Nor Azman and Ivković, Nikola and Akunzada, Adnan},
title = {{Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering}},
journal = {Scientific reports},
year = {2026},
month = jun,
volume = {16},
number = {1},
pages = {25351},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-54535-8},
url = {https://doi.org/10.1038/s41598-026-54535-8},
pmid = {42236773},
pmcid = {PMC13473467}
}

RIS

TY - JOUR
AU - Kehkashan, Tanzila
AU - Abdelhaq, Maha
AU - Abdullah, Muhammad
AU - Ahmad, Sharifah Sakinah Syed
AU - Ismail, Nor Azman
AU - Ivković, Nikola
AU - Akunzada, Adnan
TI - Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/06/03
VL - 16
IS - 1
SP - 25351
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-54535-8
UR - https://doi.org/10.1038/s41598-026-54535-8
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-54535-8",
"type": "article-journal",
"title": "Adaptive confidence ensemble reranking for reliable knowledge-intensive question answering",
"container-title": "Scientific reports",
"author": [
{
"family": "Kehkashan",
"given": "Tanzila"
},
{
"family": "Abdelhaq",
"given": "Maha"
},
{
"family": "Abdullah",
"given": "Muhammad"
},
{
"family": "Ahmad",
"given": "Sharifah Sakinah Syed"
},
{
"family": "Ismail",
"given": "Nor Azman"
},
{
"family": "Ivković",
"given": "Nikola"
},
{
"family": "Akunzada",
"given": "Adnan"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "25351",
"DOI": "10.1038/s41598-026-54535-8",
"PMID": "42236773",
"PMCID": "PMC13473467",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-54535-8",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
3
]
]
}
}

Similar papers

No other paper with a page shares enough with this one yet: tools, categories, datasets, references or authors.

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.