@inproceedings{mondal-2026-plurva,
title = "{P}lur{VA}-{LLM}-2026 Shared Task {T}rack-1 and 2: Preference Learning for Pluralistic Value Alignment",
author = "Mondal, Joydeb",
editor = "Xiong, Deyi and
Branco, Ant{\'o}nio and
Zhang, Hongming and
Dong, Yue and
Wang, Benyou and
Zhang, Wenxuan and
Zhou, Li and
Zheng, Jingting",
booktitle = "Proceedings of the First Workshop on Pluralistic Value Alignment of {LLM}s",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.plurvallm-1.8/",
pages = "98--103",
ISBN = "979-8-89176-453-8",
abstract = "We describe the Modgenix submissions to both tracks of the PlurVA-LLM 2026 Shared Task on pluralistic value alignment across China, Indonesia, and Sri Lanka. For the resource-constrained track, we use one dense 7.94B-parameter Gemma 4 E4B model for all three datasets. We recast each option as a binary candidate judgment and train rank-8 LoRA parameters using classification and pair- wise preference losses. Deterministic augmen- tation permutes answer positions, balances lan- guages, and creates a small Chinese core- action view. For the open track, we addition- ally evaluate a single GPT-5.4 model with ver- sioned multilingual prompts; its best macro accuracy is 0.795. The compact preference- trained system is stronger, so we submit it un- changed to both tracks. It obtains accuracies of 0.788, 0.683, and 0.954 on the Chinese, In- donesian, and Sri Lankan hidden sets, respec- tively, for a macro-average of 0.808 and first place on both final leaderboards. Error anal- ysis associates candidate preference learning with fewer downside-salience errors, while an objective mismatch between Indonesian anno- tator votes and consensus evaluation remains a key limitation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondal-2026-plurva">
<titleInfo>
<title>PlurVA-LLM-2026 Shared Task Track-1 and 2: Preference Learning for Pluralistic Value Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joydeb</namePart>
<namePart type="family">Mondal</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 First Workshop on Pluralistic Value Alignment of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benyou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingting</namePart>
<namePart type="family">Zheng</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">979-8-89176-453-8</identifier>
</relatedItem>
<abstract>We describe the Modgenix submissions to both tracks of the PlurVA-LLM 2026 Shared Task on pluralistic value alignment across China, Indonesia, and Sri Lanka. For the resource-constrained track, we use one dense 7.94B-parameter Gemma 4 E4B model for all three datasets. We recast each option as a binary candidate judgment and train rank-8 LoRA parameters using classification and pair- wise preference losses. Deterministic augmen- tation permutes answer positions, balances lan- guages, and creates a small Chinese core- action view. For the open track, we addition- ally evaluate a single GPT-5.4 model with ver- sioned multilingual prompts; its best macro accuracy is 0.795. The compact preference- trained system is stronger, so we submit it un- changed to both tracks. It obtains accuracies of 0.788, 0.683, and 0.954 on the Chinese, In- donesian, and Sri Lankan hidden sets, respec- tively, for a macro-average of 0.808 and first place on both final leaderboards. Error anal- ysis associates candidate preference learning with fewer downside-salience errors, while an objective mismatch between Indonesian anno- tator votes and consensus evaluation remains a key limitation.</abstract>
<identifier type="citekey">mondal-2026-plurva</identifier>
<location>
<url>https://aclanthology.org/2026.plurvallm-1.8/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>98</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PlurVA-LLM-2026 Shared Task Track-1 and 2: Preference Learning for Pluralistic Value Alignment
%A Mondal, Joydeb
%Y Xiong, Deyi
%Y Branco, António
%Y Zhang, Hongming
%Y Dong, Yue
%Y Wang, Benyou
%Y Zhang, Wenxuan
%Y Zhou, Li
%Y Zheng, Jingting
%S Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-453-8
%F mondal-2026-plurva
%X We describe the Modgenix submissions to both tracks of the PlurVA-LLM 2026 Shared Task on pluralistic value alignment across China, Indonesia, and Sri Lanka. For the resource-constrained track, we use one dense 7.94B-parameter Gemma 4 E4B model for all three datasets. We recast each option as a binary candidate judgment and train rank-8 LoRA parameters using classification and pair- wise preference losses. Deterministic augmen- tation permutes answer positions, balances lan- guages, and creates a small Chinese core- action view. For the open track, we addition- ally evaluate a single GPT-5.4 model with ver- sioned multilingual prompts; its best macro accuracy is 0.795. The compact preference- trained system is stronger, so we submit it un- changed to both tracks. It obtains accuracies of 0.788, 0.683, and 0.954 on the Chinese, In- donesian, and Sri Lankan hidden sets, respec- tively, for a macro-average of 0.808 and first place on both final leaderboards. Error anal- ysis associates candidate preference learning with fewer downside-salience errors, while an objective mismatch between Indonesian anno- tator votes and consensus evaluation remains a key limitation.
%U https://aclanthology.org/2026.plurvallm-1.8/
%P 98-103
Markdown (Informal)
[PlurVA-LLM-2026 Shared Task Track-1 and 2: Preference Learning for Pluralistic Value Alignment](https://aclanthology.org/2026.plurvallm-1.8/) (Mondal, PlurVA-LLM 2026)
ACL