@inproceedings{jing-etal-2026-tsaqa,
title = "{TSAQA}: Time Series Analysis Question And Answering Benchmark",
author = "Jing, Baoyu and
Chen, Sanhorn and
Zheng, Lecheng and
Liu, Boyu and
Li, Zihao and
Zou, Jiaru and
Wei, Tianxin and
Liu, Zhining and
Zeng, Zhichen and
Qiu, Ruizhong and
Lin, Xiao and
Yan, Yuchen and
Fu, Dongqi and
Ni, Jingchao and
He, Jingrui and
Tong, Hanghang",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.74/",
pages = "944--979",
ISBN = "979-8-89176-423-1",
abstract = "Time series data are integral to applications across domains such as finance, healthcare, transportation, and environmental science.While recent work has begun to explore time series question answering (QA), existing benchmarks still provide limited coverage of analytical capabilities under a standardized evaluation framework. We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities. TSAQA integrates 6 diverse tasks under a single framework ranging fromconventional analysis, including anomaly detection and classification, to advanced analysis, such as characterization, comparison, datatransformation, and temporal relationship analysis. Spanning 210k samples across 13 domains, the dataset employs diverse formats, including true-or-false (TF), multiple-choice (MC), and a novel puzzling (PZ), to comprehensively assess time series analysis. Zero-shotevaluation shows that TSAQA remains challenging for current Large Language Models (LLMs): best-performing commercial model,Gemini-2.5-Flash, achieves 65.08 average accuracy. Although instruction tuning improves open-source models' performance: the best-performing model, LLaMA-3.1-8B, shows significant room for improvement. We further evaluate language-capable time series foundation models (TSFMs), showing that TSAQA extends beyond general-purpose LLMs. The data are available in https://huggingface.co/datasets/TSAQA/TSAQA-Benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jing-etal-2026-tsaqa">
<titleInfo>
<title>TSAQA: Time Series Analysis Question And Answering Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baoyu</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanhorn</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lecheng</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaru</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianxin</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhining</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhichen</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruizhong</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongqi</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingchao</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingrui</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanghang</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>Time series data are integral to applications across domains such as finance, healthcare, transportation, and environmental science.While recent work has begun to explore time series question answering (QA), existing benchmarks still provide limited coverage of analytical capabilities under a standardized evaluation framework. We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities. TSAQA integrates 6 diverse tasks under a single framework ranging fromconventional analysis, including anomaly detection and classification, to advanced analysis, such as characterization, comparison, datatransformation, and temporal relationship analysis. Spanning 210k samples across 13 domains, the dataset employs diverse formats, including true-or-false (TF), multiple-choice (MC), and a novel puzzling (PZ), to comprehensively assess time series analysis. Zero-shotevaluation shows that TSAQA remains challenging for current Large Language Models (LLMs): best-performing commercial model,Gemini-2.5-Flash, achieves 65.08 average accuracy. Although instruction tuning improves open-source models’ performance: the best-performing model, LLaMA-3.1-8B, shows significant room for improvement. We further evaluate language-capable time series foundation models (TSFMs), showing that TSAQA extends beyond general-purpose LLMs. The data are available in https://huggingface.co/datasets/TSAQA/TSAQA-Benchmark.</abstract>
<identifier type="citekey">jing-etal-2026-tsaqa</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.74/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>944</start>
<end>979</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TSAQA: Time Series Analysis Question And Answering Benchmark
%A Jing, Baoyu
%A Chen, Sanhorn
%A Zheng, Lecheng
%A Liu, Boyu
%A Li, Zihao
%A Zou, Jiaru
%A Wei, Tianxin
%A Liu, Zhining
%A Zeng, Zhichen
%A Qiu, Ruizhong
%A Lin, Xiao
%A Yan, Yuchen
%A Fu, Dongqi
%A Ni, Jingchao
%A He, Jingrui
%A Tong, Hanghang
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F jing-etal-2026-tsaqa
%X Time series data are integral to applications across domains such as finance, healthcare, transportation, and environmental science.While recent work has begun to explore time series question answering (QA), existing benchmarks still provide limited coverage of analytical capabilities under a standardized evaluation framework. We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities. TSAQA integrates 6 diverse tasks under a single framework ranging fromconventional analysis, including anomaly detection and classification, to advanced analysis, such as characterization, comparison, datatransformation, and temporal relationship analysis. Spanning 210k samples across 13 domains, the dataset employs diverse formats, including true-or-false (TF), multiple-choice (MC), and a novel puzzling (PZ), to comprehensively assess time series analysis. Zero-shotevaluation shows that TSAQA remains challenging for current Large Language Models (LLMs): best-performing commercial model,Gemini-2.5-Flash, achieves 65.08 average accuracy. Although instruction tuning improves open-source models’ performance: the best-performing model, LLaMA-3.1-8B, shows significant room for improvement. We further evaluate language-capable time series foundation models (TSFMs), showing that TSAQA extends beyond general-purpose LLMs. The data are available in https://huggingface.co/datasets/TSAQA/TSAQA-Benchmark.
%U https://aclanthology.org/2026.gem-main.74/
%P 944-979
Markdown (Informal)
[TSAQA: Time Series Analysis Question And Answering Benchmark](https://aclanthology.org/2026.gem-main.74/) (Jing et al., GEM 2026)
ACL
- Baoyu Jing, Sanhorn Chen, Lecheng Zheng, Boyu Liu, Zihao Li, Jiaru Zou, Tianxin Wei, Zhining Liu, Zhichen Zeng, Ruizhong Qiu, Xiao Lin, Yuchen Yan, Dongqi Fu, Jingchao Ni, Jingrui He, and Hanghang Tong. 2026. TSAQA: Time Series Analysis Question And Answering Benchmark. In Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM), pages 944–979, San Diego, California, USA. Association for Computational Linguistics.