@inproceedings{gupta-etal-2025-bi,
title = "{BI}-Bench : A Comprehensive Benchmark Dataset and Unsupervised Evaluation for {BI} Systems",
author = "Gupta, Ankush and
Aggarwal, Aniya and
Bithel, Shivangi and
Agarwal, Arvind",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.90/",
doi = "10.18653/v1/2025.acl-industry.90",
pages = "1287--1299",
ISBN = "979-8-89176-288-6",
abstract = "A comprehensive benchmark is crucial for evaluating automated Business Intelligence (BI) systems and their real-world effectiveness. We propose BI-Bench, a holistic, end-to-end benchmarking framework that assesses BI systems based on the quality, relevance, and depth of insights. It categorizes queries into descriptive, diagnostic, predictive, and prescriptive types, aligning with practical BI needs. Our fully automated approach enables custom benchmark generation tailored to specific datasets. Additionally, we introduce an automated evaluation mechanism within BI-Bench that removes reliance on strict ground truth, ensuring scalable and adaptable assessments. By addressing key limitations, it offers a flexible and robust, user-centered methodology for advancing next-generation BI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2025-bi">
<titleInfo>
<title>BI-Bench : A Comprehensive Benchmark Dataset and Unsupervised Evaluation for BI Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankush</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aniya</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivangi</namePart>
<namePart type="family">Bithel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvind</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>A comprehensive benchmark is crucial for evaluating automated Business Intelligence (BI) systems and their real-world effectiveness. We propose BI-Bench, a holistic, end-to-end benchmarking framework that assesses BI systems based on the quality, relevance, and depth of insights. It categorizes queries into descriptive, diagnostic, predictive, and prescriptive types, aligning with practical BI needs. Our fully automated approach enables custom benchmark generation tailored to specific datasets. Additionally, we introduce an automated evaluation mechanism within BI-Bench that removes reliance on strict ground truth, ensuring scalable and adaptable assessments. By addressing key limitations, it offers a flexible and robust, user-centered methodology for advancing next-generation BI systems.</abstract>
<identifier type="citekey">gupta-etal-2025-bi</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.90</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.90/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1287</start>
<end>1299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BI-Bench : A Comprehensive Benchmark Dataset and Unsupervised Evaluation for BI Systems
%A Gupta, Ankush
%A Aggarwal, Aniya
%A Bithel, Shivangi
%A Agarwal, Arvind
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F gupta-etal-2025-bi
%X A comprehensive benchmark is crucial for evaluating automated Business Intelligence (BI) systems and their real-world effectiveness. We propose BI-Bench, a holistic, end-to-end benchmarking framework that assesses BI systems based on the quality, relevance, and depth of insights. It categorizes queries into descriptive, diagnostic, predictive, and prescriptive types, aligning with practical BI needs. Our fully automated approach enables custom benchmark generation tailored to specific datasets. Additionally, we introduce an automated evaluation mechanism within BI-Bench that removes reliance on strict ground truth, ensuring scalable and adaptable assessments. By addressing key limitations, it offers a flexible and robust, user-centered methodology for advancing next-generation BI systems.
%R 10.18653/v1/2025.acl-industry.90
%U https://aclanthology.org/2025.acl-industry.90/
%U https://doi.org/10.18653/v1/2025.acl-industry.90
%P 1287-1299
Markdown (Informal)
[BI-Bench : A Comprehensive Benchmark Dataset and Unsupervised Evaluation for BI Systems](https://aclanthology.org/2025.acl-industry.90/) (Gupta et al., ACL 2025)
ACL