@inproceedings{yang-etal-2026-slidesgen,
title = "{S}lides{G}en-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics",
author = "Yang, Yunqiao and
Li, Wenbo and
Ren, Houxing and
Lu, Zimu and
Wang, Ke and
Huang, Zhiyuan and
Zong, Zhuofan and
Zhan, Mingjie and
Li, Hongsheng",
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.1482/",
pages = "33865--33907",
ISBN = "979-8-89176-459-0",
abstract = "The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains challenging, as existing protocols often struggle to provide comparable scores across architectures or rely on uncalibrated judgments. In this paper, we introduce SlidesGen-Bench, a benchmark designed to evaluate slide generation through a lens of three core principles: universality, quantification, and reliability. First, to establish a consistent evaluation framework, we ground our primary analysis in the visual domain, treating terminal outputs as visual renderings for consistent comparison, while acknowledging format-conditional ceilings in structural editability. Second, we propose a structured computational approach that quantitatively assesses slides across three distinct dimensions{---}Content, Aesthetics, and Editability. Finally, we ensure high correlation with human preference for the highly subjective aesthetic dimensions by constructing the Slides-Align1.5k dataset. Our experiments demonstrate that SlidesGen-Bench achieves a significantly higher degree of alignment with human judgment than existing evaluation pipelines. Our code and data are released to support further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-slidesgen">
<titleInfo>
<title>SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunqiao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houxing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuofan</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingjie</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongsheng</namePart>
<namePart type="family">Li</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>The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains challenging, as existing protocols often struggle to provide comparable scores across architectures or rely on uncalibrated judgments. In this paper, we introduce SlidesGen-Bench, a benchmark designed to evaluate slide generation through a lens of three core principles: universality, quantification, and reliability. First, to establish a consistent evaluation framework, we ground our primary analysis in the visual domain, treating terminal outputs as visual renderings for consistent comparison, while acknowledging format-conditional ceilings in structural editability. Second, we propose a structured computational approach that quantitatively assesses slides across three distinct dimensions—Content, Aesthetics, and Editability. Finally, we ensure high correlation with human preference for the highly subjective aesthetic dimensions by constructing the Slides-Align1.5k dataset. Our experiments demonstrate that SlidesGen-Bench achieves a significantly higher degree of alignment with human judgment than existing evaluation pipelines. Our code and data are released to support further research.</abstract>
<identifier type="citekey">yang-etal-2026-slidesgen</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1482/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33865</start>
<end>33907</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics
%A Yang, Yunqiao
%A Li, Wenbo
%A Ren, Houxing
%A Lu, Zimu
%A Wang, Ke
%A Huang, Zhiyuan
%A Zong, Zhuofan
%A Zhan, Mingjie
%A Li, Hongsheng
%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 yang-etal-2026-slidesgen
%X The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains challenging, as existing protocols often struggle to provide comparable scores across architectures or rely on uncalibrated judgments. In this paper, we introduce SlidesGen-Bench, a benchmark designed to evaluate slide generation through a lens of three core principles: universality, quantification, and reliability. First, to establish a consistent evaluation framework, we ground our primary analysis in the visual domain, treating terminal outputs as visual renderings for consistent comparison, while acknowledging format-conditional ceilings in structural editability. Second, we propose a structured computational approach that quantitatively assesses slides across three distinct dimensions—Content, Aesthetics, and Editability. Finally, we ensure high correlation with human preference for the highly subjective aesthetic dimensions by constructing the Slides-Align1.5k dataset. Our experiments demonstrate that SlidesGen-Bench achieves a significantly higher degree of alignment with human judgment than existing evaluation pipelines. Our code and data are released to support further research.
%U https://aclanthology.org/2026.emnlp-main.1482/
%P 33865-33907
Markdown (Informal)
[SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics](https://aclanthology.org/2026.emnlp-main.1482/) (Yang et al., EMNLP 2026)
ACL
- Yunqiao Yang, Wenbo Li, Houxing Ren, Zimu Lu, Ke Wang, Zhiyuan Huang, Zhuofan Zong, Mingjie Zhan, and Hongsheng Li. 2026. SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 33865–33907, Budapest, Hungary. Association for Computational Linguistics.