@inproceedings{macko-pulver-2026-perq,
title = "{P}er{Q}: Efficient Evaluation of Multilingual Text Platform-Adaptation Quality",
author = "Macko, Dominik and
Pulver, Andrew",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.270/",
pages = "5990--6003",
ISBN = "979-8-89176-439-2",
abstract = "Since no metrics are available to evaluate specific aspects of a text, such as its personalization quality or quality of adaptation to a specific form, researchers often rely solely on large language models to evaluate such texts. Due to internal biases of individual language models, it is recommended to use multiple of them for combined evaluation, which directly increases costs of such evaluation. In this paper, a computationally efficient method (called PerQ) for evaluation of personalization quality (in terms of platform adaptation) of a given text (generated by a language model) is introduced, which is based on predicting the LLM judgments (i.e., a kind of metric distillation). A case study of comparison of generation capabilities of large and small language models shows the usability of the proposed metric in research, effectively reducing the waste of resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macko-pulver-2026-perq">
<titleInfo>
<title>PerQ: Efficient Evaluation of Multilingual Text Platform-Adaptation Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Macko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Pulver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Since no metrics are available to evaluate specific aspects of a text, such as its personalization quality or quality of adaptation to a specific form, researchers often rely solely on large language models to evaluate such texts. Due to internal biases of individual language models, it is recommended to use multiple of them for combined evaluation, which directly increases costs of such evaluation. In this paper, a computationally efficient method (called PerQ) for evaluation of personalization quality (in terms of platform adaptation) of a given text (generated by a language model) is introduced, which is based on predicting the LLM judgments (i.e., a kind of metric distillation). A case study of comparison of generation capabilities of large and small language models shows the usability of the proposed metric in research, effectively reducing the waste of resources.</abstract>
<identifier type="citekey">macko-pulver-2026-perq</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.270/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>5990</start>
<end>6003</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PerQ: Efficient Evaluation of Multilingual Text Platform-Adaptation Quality
%A Macko, Dominik
%A Pulver, Andrew
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F macko-pulver-2026-perq
%X Since no metrics are available to evaluate specific aspects of a text, such as its personalization quality or quality of adaptation to a specific form, researchers often rely solely on large language models to evaluate such texts. Due to internal biases of individual language models, it is recommended to use multiple of them for combined evaluation, which directly increases costs of such evaluation. In this paper, a computationally efficient method (called PerQ) for evaluation of personalization quality (in terms of platform adaptation) of a given text (generated by a language model) is introduced, which is based on predicting the LLM judgments (i.e., a kind of metric distillation). A case study of comparison of generation capabilities of large and small language models shows the usability of the proposed metric in research, effectively reducing the waste of resources.
%U https://aclanthology.org/2026.aacl-long.270/
%P 5990-6003
Markdown (Informal)
[PerQ: Efficient Evaluation of Multilingual Text Platform-Adaptation Quality](https://aclanthology.org/2026.aacl-long.270/) (Macko & Pulver, AACL-IJCNLP 2026)
ACL
- Dominik Macko and Andrew Pulver. 2026. PerQ: Efficient Evaluation of Multilingual Text Platform-Adaptation Quality. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5990–6003, Hengqin, China. Association for Computational Linguistics.