@inproceedings{k-etal-2025-aura,
title = "{AURA}-{QG}: Automated Unsupervised Replicable Assessment for Question Generation",
author = "K, Rajshekar and
Khadilkar, Harshad and
Bhattacharyya, Pushpak",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.159/",
pages = "2979--2992",
ISBN = "979-8-89176-298-5",
abstract = "Question Generation (QG) is central to information retrieval, education, and knowledge assessment, yet its progress is bottlenecked by unreliable and non-scalable evaluation practices. Traditional metrics fall short in structured settings like document-grounded QG, and human evaluation, while insightful, remains expensive, inconsistent, and difficult to replicate at scale. We introduce AURA-QG: an Automated, Unsupervised, Replicable Assessment pipeline that scores question sets using only the source document. It captures four orthogonal dimensions i.e., answerability, non-redundancy, coverage, and structural entropy, without needing reference questions or relative baselines. Our method is modular, efficient, and agnostic to the question generation strategy. Through extensive experiments across four domains i.e., car manuals, economic surveys, health brochures, and fiction, we demonstrate its robustness across input granularities and prompting paradigms. Chain-of-Thought prompting, which first extracts answer spans and then generates targeted questions, consistently yields higher answerability and coverage, validating the pipeline{'}s fidelity. The metrics also exhibit strong agreement with human judgments, reinforcing their reliability for practical adoption. The complete implementation of our evaluation pipeline is publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="k-etal-2025-aura">
<titleInfo>
<title>AURA-QG: Automated Unsupervised Replicable Assessment for Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajshekar</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshad</namePart>
<namePart type="family">Khadilkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Question Generation (QG) is central to information retrieval, education, and knowledge assessment, yet its progress is bottlenecked by unreliable and non-scalable evaluation practices. Traditional metrics fall short in structured settings like document-grounded QG, and human evaluation, while insightful, remains expensive, inconsistent, and difficult to replicate at scale. We introduce AURA-QG: an Automated, Unsupervised, Replicable Assessment pipeline that scores question sets using only the source document. It captures four orthogonal dimensions i.e., answerability, non-redundancy, coverage, and structural entropy, without needing reference questions or relative baselines. Our method is modular, efficient, and agnostic to the question generation strategy. Through extensive experiments across four domains i.e., car manuals, economic surveys, health brochures, and fiction, we demonstrate its robustness across input granularities and prompting paradigms. Chain-of-Thought prompting, which first extracts answer spans and then generates targeted questions, consistently yields higher answerability and coverage, validating the pipeline’s fidelity. The metrics also exhibit strong agreement with human judgments, reinforcing their reliability for practical adoption. The complete implementation of our evaluation pipeline is publicly available.</abstract>
<identifier type="citekey">k-etal-2025-aura</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.159/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2979</start>
<end>2992</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AURA-QG: Automated Unsupervised Replicable Assessment for Question Generation
%A K, Rajshekar
%A Khadilkar, Harshad
%A Bhattacharyya, Pushpak
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F k-etal-2025-aura
%X Question Generation (QG) is central to information retrieval, education, and knowledge assessment, yet its progress is bottlenecked by unreliable and non-scalable evaluation practices. Traditional metrics fall short in structured settings like document-grounded QG, and human evaluation, while insightful, remains expensive, inconsistent, and difficult to replicate at scale. We introduce AURA-QG: an Automated, Unsupervised, Replicable Assessment pipeline that scores question sets using only the source document. It captures four orthogonal dimensions i.e., answerability, non-redundancy, coverage, and structural entropy, without needing reference questions or relative baselines. Our method is modular, efficient, and agnostic to the question generation strategy. Through extensive experiments across four domains i.e., car manuals, economic surveys, health brochures, and fiction, we demonstrate its robustness across input granularities and prompting paradigms. Chain-of-Thought prompting, which first extracts answer spans and then generates targeted questions, consistently yields higher answerability and coverage, validating the pipeline’s fidelity. The metrics also exhibit strong agreement with human judgments, reinforcing their reliability for practical adoption. The complete implementation of our evaluation pipeline is publicly available.
%U https://aclanthology.org/2025.ijcnlp-long.159/
%P 2979-2992
Markdown (Informal)
[AURA-QG: Automated Unsupervised Replicable Assessment for Question Generation](https://aclanthology.org/2025.ijcnlp-long.159/) (K et al., IJCNLP-AACL 2025)
ACL
- Rajshekar K, Harshad Khadilkar, and Pushpak Bhattacharyya. 2025. AURA-QG: Automated Unsupervised Replicable Assessment for Question Generation. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2979–2992, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.