@inproceedings{zhang-etal-2026-metagai,
title = "{M}eta{GAI}: A Large-Scale and High-Quality Benchmark for Generative {AI} Model and Data Card Generation",
author = "Zhang, Haoxuan and
Li, Ruochi and
Zhang, Yang and
Liang, Zhenni and
Ding, Junhua and
Xiao, Ting and
Chen, Haihua",
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.1641/",
pages = "34910--34931",
ISBN = "979-8-89176-462-0",
abstract = "The rapid proliferation of Generative AI has created a pressing need for rigorous documentation standards that support transparency and governance. Manual creation of Model and Data Cards, however, is difficult to scale, and automated approaches lack the large-scale, high-fidelity benchmarks required for systematic evaluation. We introduce MetaGAI, a benchmark of 2,541 semantically matched document triplets constructed from academic papers, GitHub repositories, and Hugging Face artifacts. Reference cards are produced by a multi-agent pipeline of specialized Retriever, Generator, and Editor agents, and the pipeline is assessed through a four-part validation protocol. We further propose an evaluation framework that combines reference-based automated metrics with a multi-model LLM-as-a-Judge protocol, together with explicit agreement and sensitivity analyses. Among the evaluated baselines, Qwen3-30B-A3B-Instruct achieves the best observed cost{--}quality trade-off, and the results reveal a recurring tension between faithfulness and completeness. MetaGAI provides a testbed for benchmarking, training, and analyzing automated Model and Data Card generation at scale. Our data and code are available at https://github.com/haoxuan-unt2024/MetaGAI-Benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-metagai">
<titleInfo>
<title>MetaGAI: A Large-Scale and High-Quality Benchmark for Generative AI Model and Data Card Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenni</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhua</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haihua</namePart>
<namePart type="family">Chen</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>The rapid proliferation of Generative AI has created a pressing need for rigorous documentation standards that support transparency and governance. Manual creation of Model and Data Cards, however, is difficult to scale, and automated approaches lack the large-scale, high-fidelity benchmarks required for systematic evaluation. We introduce MetaGAI, a benchmark of 2,541 semantically matched document triplets constructed from academic papers, GitHub repositories, and Hugging Face artifacts. Reference cards are produced by a multi-agent pipeline of specialized Retriever, Generator, and Editor agents, and the pipeline is assessed through a four-part validation protocol. We further propose an evaluation framework that combines reference-based automated metrics with a multi-model LLM-as-a-Judge protocol, together with explicit agreement and sensitivity analyses. Among the evaluated baselines, Qwen3-30B-A3B-Instruct achieves the best observed cost–quality trade-off, and the results reveal a recurring tension between faithfulness and completeness. MetaGAI provides a testbed for benchmarking, training, and analyzing automated Model and Data Card generation at scale. Our data and code are available at https://github.com/haoxuan-unt2024/MetaGAI-Benchmark.</abstract>
<identifier type="citekey">zhang-etal-2026-metagai</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1641/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>34910</start>
<end>34931</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MetaGAI: A Large-Scale and High-Quality Benchmark for Generative AI Model and Data Card Generation
%A Zhang, Haoxuan
%A Li, Ruochi
%A Zhang, Yang
%A Liang, Zhenni
%A Ding, Junhua
%A Xiao, Ting
%A Chen, Haihua
%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 zhang-etal-2026-metagai
%X The rapid proliferation of Generative AI has created a pressing need for rigorous documentation standards that support transparency and governance. Manual creation of Model and Data Cards, however, is difficult to scale, and automated approaches lack the large-scale, high-fidelity benchmarks required for systematic evaluation. We introduce MetaGAI, a benchmark of 2,541 semantically matched document triplets constructed from academic papers, GitHub repositories, and Hugging Face artifacts. Reference cards are produced by a multi-agent pipeline of specialized Retriever, Generator, and Editor agents, and the pipeline is assessed through a four-part validation protocol. We further propose an evaluation framework that combines reference-based automated metrics with a multi-model LLM-as-a-Judge protocol, together with explicit agreement and sensitivity analyses. Among the evaluated baselines, Qwen3-30B-A3B-Instruct achieves the best observed cost–quality trade-off, and the results reveal a recurring tension between faithfulness and completeness. MetaGAI provides a testbed for benchmarking, training, and analyzing automated Model and Data Card generation at scale. Our data and code are available at https://github.com/haoxuan-unt2024/MetaGAI-Benchmark.
%U https://aclanthology.org/2026.findings-emnlp.1641/
%P 34910-34931
Markdown (Informal)
[MetaGAI: A Large-Scale and High-Quality Benchmark for Generative AI Model and Data Card Generation](https://aclanthology.org/2026.findings-emnlp.1641/) (Zhang et al., Findings 2026)
ACL