@inproceedings{ghazaryan-donmez-2026-better,
title = "Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks",
author = {Ghazaryan, Gayane and
D{\"o}nmez, Esra},
editor = "Xu, Shanshan and
T.Y.S.S., Santosh and
Kurniawan, Kemal and
Peng, Siyao and
Wallbridge, Sarenne and
Koto, Fajri and
Dziri, Nouha and
Plank, Barbara",
booktitle = "Proceedings of the First Workshop on Pluralistic {AI} {NLP}: Diversity-aware, Sociotechnical, Responsible Alignment ({PANDORA} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.pandora-1.8/",
pages = "149--168",
ISBN = "979-8-89176-484-2",
abstract = "Reward models are central to LLM alignment, yet current benchmarks reveal little about how they represent diverse and sometimes competing social preferences. We extend reward-model evaluation to four socially consequential domains: bias, safety, morality, and ethical reasoning. Our analysis shows that strong benchmark performance can obscure important differences in social behavior. Models may avoid some stereotypes while reinforcing others, and aggregate bias scores can hide these opposing tendencies. We also find that stronger stereotype avoidance can come at the expense of contextual faithfulness, revealing a trade-off between social bias mitigation and sensitivity to context. Across a broad set of reward models, standard benchmark performance is only inconsistently related to socially aligned behavior. These results show that stronger reward models are not uniformly better at navigating pluralistic social expectations and motivate more direct evaluation of the social preferences encoded in reward models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghazaryan-donmez-2026-better">
<titleInfo>
<title>Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gayane</namePart>
<namePart type="family">Ghazaryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esra</namePart>
<namePart type="family">Dönmez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pluralistic AI NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Kurniawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarenne</namePart>
<namePart type="family">Wallbridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-484-2</identifier>
</relatedItem>
<abstract>Reward models are central to LLM alignment, yet current benchmarks reveal little about how they represent diverse and sometimes competing social preferences. We extend reward-model evaluation to four socially consequential domains: bias, safety, morality, and ethical reasoning. Our analysis shows that strong benchmark performance can obscure important differences in social behavior. Models may avoid some stereotypes while reinforcing others, and aggregate bias scores can hide these opposing tendencies. We also find that stronger stereotype avoidance can come at the expense of contextual faithfulness, revealing a trade-off between social bias mitigation and sensitivity to context. Across a broad set of reward models, standard benchmark performance is only inconsistently related to socially aligned behavior. These results show that stronger reward models are not uniformly better at navigating pluralistic social expectations and motivate more direct evaluation of the social preferences encoded in reward models.</abstract>
<identifier type="citekey">ghazaryan-donmez-2026-better</identifier>
<location>
<url>https://aclanthology.org/2026.pandora-1.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>149</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks
%A Ghazaryan, Gayane
%A Dönmez, Esra
%Y Xu, Shanshan
%Y T.Y.S.S., Santosh
%Y Kurniawan, Kemal
%Y Peng, Siyao
%Y Wallbridge, Sarenne
%Y Koto, Fajri
%Y Dziri, Nouha
%Y Plank, Barbara
%S Proceedings of the First Workshop on Pluralistic AI NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-484-2
%F ghazaryan-donmez-2026-better
%X Reward models are central to LLM alignment, yet current benchmarks reveal little about how they represent diverse and sometimes competing social preferences. We extend reward-model evaluation to four socially consequential domains: bias, safety, morality, and ethical reasoning. Our analysis shows that strong benchmark performance can obscure important differences in social behavior. Models may avoid some stereotypes while reinforcing others, and aggregate bias scores can hide these opposing tendencies. We also find that stronger stereotype avoidance can come at the expense of contextual faithfulness, revealing a trade-off between social bias mitigation and sensitivity to context. Across a broad set of reward models, standard benchmark performance is only inconsistently related to socially aligned behavior. These results show that stronger reward models are not uniformly better at navigating pluralistic social expectations and motivate more direct evaluation of the social preferences encoded in reward models.
%U https://aclanthology.org/2026.pandora-1.8/
%P 149-168
Markdown (Informal)
[Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks](https://aclanthology.org/2026.pandora-1.8/) (Ghazaryan & Dönmez, PANDORA 2026)
ACL