@inproceedings{eshuijs-etal-2026-balancing,
title = "Balancing the Scales: Reinforcement Learning for Fair Classification",
author = "Eshuijs, Leon and
Wang, Shihan and
Fokkens, Antske",
editor = "Pranav, A and
Basile, Valerio and
Falk, Neele and
Jurgens, David and
Lapesa, Gabriella and
Lauscher, Anne and
Lo, Soda Marem",
booktitle = "Proceedings of the Second Workshop of Identity Aware {AI}",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2026.iaai-1.4/",
doi = "10.63317/4df2efew2ftw",
pages = "32--46",
abstract = "Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent approaches have shifted towards algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its ability to learn through interaction and adjust reward functions to encourage desired behaviors, presents a promising approach in this domain. In this paper, we conduct an exploratory evaluation of RL for addressing bias in imbalanced classification by scaling the reward function. We employ the contextual multi-armed bandit framework, adapt three popular RL algorithms, and conduct an extensive empirical evaluation of their relative strengths and limitations. Through this analysis, we contribute meaningful evidence to the ongoing debate between algorithmic and representational fairness approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eshuijs-etal-2026-balancing">
<titleInfo>
<title>Balancing the Scales: Reinforcement Learning for Fair Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Eshuijs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antske</namePart>
<namePart type="family">Fokkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop of Identity Aware AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Pranav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Lauscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soda</namePart>
<namePart type="given">Marem</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent approaches have shifted towards algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its ability to learn through interaction and adjust reward functions to encourage desired behaviors, presents a promising approach in this domain. In this paper, we conduct an exploratory evaluation of RL for addressing bias in imbalanced classification by scaling the reward function. We employ the contextual multi-armed bandit framework, adapt three popular RL algorithms, and conduct an extensive empirical evaluation of their relative strengths and limitations. Through this analysis, we contribute meaningful evidence to the ongoing debate between algorithmic and representational fairness approaches.</abstract>
<identifier type="citekey">eshuijs-etal-2026-balancing</identifier>
<identifier type="doi">10.63317/4df2efew2ftw</identifier>
<location>
<url>https://aclanthology.org/2026.iaai-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>32</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balancing the Scales: Reinforcement Learning for Fair Classification
%A Eshuijs, Leon
%A Wang, Shihan
%A Fokkens, Antske
%Y Pranav, A.
%Y Basile, Valerio
%Y Falk, Neele
%Y Jurgens, David
%Y Lapesa, Gabriella
%Y Lauscher, Anne
%Y Lo, Soda Marem
%S Proceedings of the Second Workshop of Identity Aware AI
%D 2026
%8 May
%I European Language Resources Association
%C Palma de Mallorca, Spain
%F eshuijs-etal-2026-balancing
%X Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent approaches have shifted towards algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its ability to learn through interaction and adjust reward functions to encourage desired behaviors, presents a promising approach in this domain. In this paper, we conduct an exploratory evaluation of RL for addressing bias in imbalanced classification by scaling the reward function. We employ the contextual multi-armed bandit framework, adapt three popular RL algorithms, and conduct an extensive empirical evaluation of their relative strengths and limitations. Through this analysis, we contribute meaningful evidence to the ongoing debate between algorithmic and representational fairness approaches.
%R 10.63317/4df2efew2ftw
%U https://aclanthology.org/2026.iaai-1.4/
%U https://doi.org/10.63317/4df2efew2ftw
%P 32-46
Markdown (Informal)
[Balancing the Scales: Reinforcement Learning for Fair Classification](https://aclanthology.org/2026.iaai-1.4/) (Eshuijs et al., iaai 2026)
ACL