@inproceedings{hanya-etal-2026-insightchain,
title = "{I}nsight{C}hain: Optimized Chain-of-Insight Analytics for {LLM}-driven Data Visualization",
author = "Hanya, Sun and
Zhang, Chen and
Liang, Sheng and
Zhang, Yongyue and
Liu, Yong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.771/",
doi = "10.18653/2026.findings-emnlp.771",
pages = "16273--16295",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-step visualization prompting pipeline (Explore-Focus-Test-Present) that emulates expert analytical workflows for complex data visualization, together with VG-COPRO, a novel automatic prompt optimization (APO) algorithm for jointly optimizing pipeline performance. To further bridge the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. Experiments on public datasets demonstrate that InsightChain consistently outperforms competing prompting baselines. We further show that VG-COPRO is more effective than existing APO methods at optimizing chain-based visualization prompting strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hanya-etal-2026-insightchain">
<titleInfo>
<title>InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Hanya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongyue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Liu</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-step visualization prompting pipeline (Explore-Focus-Test-Present) that emulates expert analytical workflows for complex data visualization, together with VG-COPRO, a novel automatic prompt optimization (APO) algorithm for jointly optimizing pipeline performance. To further bridge the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. Experiments on public datasets demonstrate that InsightChain consistently outperforms competing prompting baselines. We further show that VG-COPRO is more effective than existing APO methods at optimizing chain-based visualization prompting strategies.</abstract>
<identifier type="citekey">hanya-etal-2026-insightchain</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.771</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.771/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>16273</start>
<end>16295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization
%A Hanya, Sun
%A Zhang, Chen
%A Liang, Sheng
%A Zhang, Yongyue
%A Liu, Yong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hanya-etal-2026-insightchain
%X Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-step visualization prompting pipeline (Explore-Focus-Test-Present) that emulates expert analytical workflows for complex data visualization, together with VG-COPRO, a novel automatic prompt optimization (APO) algorithm for jointly optimizing pipeline performance. To further bridge the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. Experiments on public datasets demonstrate that InsightChain consistently outperforms competing prompting baselines. We further show that VG-COPRO is more effective than existing APO methods at optimizing chain-based visualization prompting strategies.
%R 10.18653/2026.findings-emnlp.771
%U https://aclanthology.org/2026.findings-emnlp.771/
%U https://doi.org/10.18653/2026.findings-emnlp.771
%P 16273-16295
Markdown (Informal)
[InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization](https://aclanthology.org/2026.findings-emnlp.771/) (Hanya et al., Findings 2026)
ACL