@inproceedings{pinninti-etal-2026-dynamic,
title = "Dynamic Model Switching to Mitigate Outdated Knowledge in Large Language Models",
author = "Pinninti, Ramakrishna and
Kamila, Sabyasachi and
Mazumder, Ayan and
Hasanuzzaman, Mohammed",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.195/",
doi = "10.63317/2n9poorzn8s3",
pages = "2490--2500",
abstract = "Generating timely and accurate content is a significant challenge for Large Language Models (LLMs). Obsolete information reduces their reliability and user trust. To overcome the limitations of single models in adapting to evolving information, we propose a dynamic switching model. A multitask trained switch model objective, adaptively picks between a large model that does not have recent information and a smaller model fine-tuned on recent information using contextual and temporal indicators. This method incorporates semantic update detection and temporal switching, which predicts text obsolescence through aggregation of reward signals. For evaluation, we curated the Temporally-aware Dynamic Dataset (TaDD) on Wikipedia and Guardian articles, which are frequently updated. Our framework achieves a balanced precision-recall trade-off on five datasets without continuous retraining, which shows that the model is efficient and adaptable compared to static pretrained models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pinninti-etal-2026-dynamic">
<titleInfo>
<title>Dynamic Model Switching to Mitigate Outdated Knowledge in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramakrishna</namePart>
<namePart type="family">Pinninti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayan</namePart>
<namePart type="family">Mazumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating timely and accurate content is a significant challenge for Large Language Models (LLMs). Obsolete information reduces their reliability and user trust. To overcome the limitations of single models in adapting to evolving information, we propose a dynamic switching model. A multitask trained switch model objective, adaptively picks between a large model that does not have recent information and a smaller model fine-tuned on recent information using contextual and temporal indicators. This method incorporates semantic update detection and temporal switching, which predicts text obsolescence through aggregation of reward signals. For evaluation, we curated the Temporally-aware Dynamic Dataset (TaDD) on Wikipedia and Guardian articles, which are frequently updated. Our framework achieves a balanced precision-recall trade-off on five datasets without continuous retraining, which shows that the model is efficient and adaptable compared to static pretrained models.</abstract>
<identifier type="citekey">pinninti-etal-2026-dynamic</identifier>
<identifier type="doi">10.63317/2n9poorzn8s3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.195/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2490</start>
<end>2500</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynamic Model Switching to Mitigate Outdated Knowledge in Large Language Models
%A Pinninti, Ramakrishna
%A Kamila, Sabyasachi
%A Mazumder, Ayan
%A Hasanuzzaman, Mohammed
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F pinninti-etal-2026-dynamic
%X Generating timely and accurate content is a significant challenge for Large Language Models (LLMs). Obsolete information reduces their reliability and user trust. To overcome the limitations of single models in adapting to evolving information, we propose a dynamic switching model. A multitask trained switch model objective, adaptively picks between a large model that does not have recent information and a smaller model fine-tuned on recent information using contextual and temporal indicators. This method incorporates semantic update detection and temporal switching, which predicts text obsolescence through aggregation of reward signals. For evaluation, we curated the Temporally-aware Dynamic Dataset (TaDD) on Wikipedia and Guardian articles, which are frequently updated. Our framework achieves a balanced precision-recall trade-off on five datasets without continuous retraining, which shows that the model is efficient and adaptable compared to static pretrained models.
%R 10.63317/2n9poorzn8s3
%U https://aclanthology.org/2026.lrec-1.195/
%U https://doi.org/10.63317/2n9poorzn8s3
%P 2490-2500
Markdown (Informal)
[Dynamic Model Switching to Mitigate Outdated Knowledge in Large Language Models](https://aclanthology.org/2026.lrec-1.195/) (Pinninti et al., LREC 2026)
ACL