@inproceedings{jeon-etal-2026-bridging,
title = "Bridging Time Series and Language via Query-Adaptive Multi-Granularity Routing for Temporal Reasoning",
author = "Jeon, Hyuna and
Lee, Jaeyoung and
Kim, Misuk",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1397/",
pages = "31917--31935",
ISBN = "979-8-89176-459-0",
abstract = "Time-Series Question Answering (TSQA) aims to interpret time-series information and generate answers according to the intent of natural language questions. However, in TSQA, the required temporal granularity and reasoning scope vary across queries, making it crucial to effectively organize the time-series information needed for each query. In this study, we propose TiMER (**Ti**me-series and language alignment with **M**ulti-granularity **E**xpert **R**outing), a time-series-language alignment framework that selectively constructs multi-granularity time-series information according to query intent and connects it to the LLM input space. Experimental results on a large-scale TSQA benchmark show that TiMER achieves an overall accuracy of 81.02{\%} using only a small number of external alignment modules while keeping the LLM frozen, outperforming various LLM-based baselines. In addition, extensive ablation studies verify the effectiveness of each component. This study presents an effective direction for natural language-based time-series understanding and temporal reasoning by dynamically organizing and utilizing time-series information according to query intent. The code is publicly available at https://github.com/hyuna0926/TiMER{\_}paper."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-etal-2026-bridging">
<titleInfo>
<title>Bridging Time Series and Language via Query-Adaptive Multi-Granularity Routing for Temporal Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyuna</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeyoung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Misuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Time-Series Question Answering (TSQA) aims to interpret time-series information and generate answers according to the intent of natural language questions. However, in TSQA, the required temporal granularity and reasoning scope vary across queries, making it crucial to effectively organize the time-series information needed for each query. In this study, we propose TiMER (**Ti**me-series and language alignment with **M**ulti-granularity **E**xpert **R**outing), a time-series-language alignment framework that selectively constructs multi-granularity time-series information according to query intent and connects it to the LLM input space. Experimental results on a large-scale TSQA benchmark show that TiMER achieves an overall accuracy of 81.02% using only a small number of external alignment modules while keeping the LLM frozen, outperforming various LLM-based baselines. In addition, extensive ablation studies verify the effectiveness of each component. This study presents an effective direction for natural language-based time-series understanding and temporal reasoning by dynamically organizing and utilizing time-series information according to query intent. The code is publicly available at https://github.com/hyuna0926/TiMER_paper.</abstract>
<identifier type="citekey">jeon-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1397/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31917</start>
<end>31935</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging Time Series and Language via Query-Adaptive Multi-Granularity Routing for Temporal Reasoning
%A Jeon, Hyuna
%A Lee, Jaeyoung
%A Kim, Misuk
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F jeon-etal-2026-bridging
%X Time-Series Question Answering (TSQA) aims to interpret time-series information and generate answers according to the intent of natural language questions. However, in TSQA, the required temporal granularity and reasoning scope vary across queries, making it crucial to effectively organize the time-series information needed for each query. In this study, we propose TiMER (**Ti**me-series and language alignment with **M**ulti-granularity **E**xpert **R**outing), a time-series-language alignment framework that selectively constructs multi-granularity time-series information according to query intent and connects it to the LLM input space. Experimental results on a large-scale TSQA benchmark show that TiMER achieves an overall accuracy of 81.02% using only a small number of external alignment modules while keeping the LLM frozen, outperforming various LLM-based baselines. In addition, extensive ablation studies verify the effectiveness of each component. This study presents an effective direction for natural language-based time-series understanding and temporal reasoning by dynamically organizing and utilizing time-series information according to query intent. The code is publicly available at https://github.com/hyuna0926/TiMER_paper.
%U https://aclanthology.org/2026.emnlp-main.1397/
%P 31917-31935
Markdown (Informal)
[Bridging Time Series and Language via Query-Adaptive Multi-Granularity Routing for Temporal Reasoning](https://aclanthology.org/2026.emnlp-main.1397/) (Jeon et al., EMNLP 2026)
ACL