@inproceedings{badshah-etal-2025-clev,
title = "{CLEV}: {LLM}-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering",
author = "Badshah, Sher and
Moustafa, Moamen and
Sajjad, Hassan",
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.findings-ijcnlp.93/",
pages = "1513--1531",
ISBN = "979-8-89176-303-6",
abstract = "Evaluating free-form Question-Answering (QA) remains a challenge due to its diverse and open-ended nature. Traditional automatic metrics fail to capture semantic equivalence or accommodate the variability of open-ended responses. Leveraging Large Language Models (LLMs) as evaluators offers a promising alternative due to their strong language understanding and instruction-following capabilities. We propose the Consensus via Lightweight Efficient Voting (CLEV), which employs two primary LLMs as judges and engages a third judge only in cases of disagreement. This approach prioritizes evaluation reliability while reducing unnecessary computational demands. Through experiments, including human evaluation, we demonstrate CLEV{'}s ability to provide consistent, scalable, and resource-efficient assessments, establishing it as a robust framework for evaluating LLMs on free-form QA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="badshah-etal-2025-clev">
<titleInfo>
<title>CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sher</namePart>
<namePart type="family">Badshah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moamen</namePart>
<namePart type="family">Moustafa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</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">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Evaluating free-form Question-Answering (QA) remains a challenge due to its diverse and open-ended nature. Traditional automatic metrics fail to capture semantic equivalence or accommodate the variability of open-ended responses. Leveraging Large Language Models (LLMs) as evaluators offers a promising alternative due to their strong language understanding and instruction-following capabilities. We propose the Consensus via Lightweight Efficient Voting (CLEV), which employs two primary LLMs as judges and engages a third judge only in cases of disagreement. This approach prioritizes evaluation reliability while reducing unnecessary computational demands. Through experiments, including human evaluation, we demonstrate CLEV’s ability to provide consistent, scalable, and resource-efficient assessments, establishing it as a robust framework for evaluating LLMs on free-form QA.</abstract>
<identifier type="citekey">badshah-etal-2025-clev</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.93/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1513</start>
<end>1531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering
%A Badshah, Sher
%A Moustafa, Moamen
%A Sajjad, Hassan
%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
%@ 979-8-89176-303-6
%F badshah-etal-2025-clev
%X Evaluating free-form Question-Answering (QA) remains a challenge due to its diverse and open-ended nature. Traditional automatic metrics fail to capture semantic equivalence or accommodate the variability of open-ended responses. Leveraging Large Language Models (LLMs) as evaluators offers a promising alternative due to their strong language understanding and instruction-following capabilities. We propose the Consensus via Lightweight Efficient Voting (CLEV), which employs two primary LLMs as judges and engages a third judge only in cases of disagreement. This approach prioritizes evaluation reliability while reducing unnecessary computational demands. Through experiments, including human evaluation, we demonstrate CLEV’s ability to provide consistent, scalable, and resource-efficient assessments, establishing it as a robust framework for evaluating LLMs on free-form QA.
%U https://aclanthology.org/2025.findings-ijcnlp.93/
%P 1513-1531
Markdown (Informal)
[CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering](https://aclanthology.org/2025.findings-ijcnlp.93/) (Badshah et al., Findings 2025)
ACL