@inproceedings{ma-etal-2026-personalizing,
title = "Personalizing {LLM}s with Binary Feedback: A Preference-Calibrated Optimization Framework",
author = "Ma, Xilai and
Zhao, Liye and
Yao, Weijun and
Di, Haibing and
Wang, Wenya and
Li, Jing",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1222/",
pages = "26539--26555",
ISBN = "979-8-89176-390-6",
abstract = "Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences.Existing methods often focus on isolated user histories, neglecting the essential role of inter-user differences.We propose C-BPO, a framework that personalizes LLMs via preference-calibrated binary signals.By treating target user data as positive feedback and other users' data as an auxiliary set of implicit negative signals, C-BPO captures distinct inter-user differences.To mitigate the preference overlap issue, where shared task knowledge is erroneously penalized, we derive an objective grounded in Positive-Unlabeled (PU) learning theory.This approach purifies negative signals by subtracting ``positive bias'', ensuring alignment with unique idiosyncrasies without compromising general helpfulness.Empirical experiments across various personalization tasks and backbone LLMs show C-BPO consistently outperforms baselines, demonstrating the efficacy of preference-calibrated binary signals in modeling inter-user differences."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2026-personalizing">
<titleInfo>
<title>Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xilai</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liye</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijun</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haibing</namePart>
<namePart type="family">Di</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenya</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences.Existing methods often focus on isolated user histories, neglecting the essential role of inter-user differences.We propose C-BPO, a framework that personalizes LLMs via preference-calibrated binary signals.By treating target user data as positive feedback and other users’ data as an auxiliary set of implicit negative signals, C-BPO captures distinct inter-user differences.To mitigate the preference overlap issue, where shared task knowledge is erroneously penalized, we derive an objective grounded in Positive-Unlabeled (PU) learning theory.This approach purifies negative signals by subtracting “positive bias”, ensuring alignment with unique idiosyncrasies without compromising general helpfulness.Empirical experiments across various personalization tasks and backbone LLMs show C-BPO consistently outperforms baselines, demonstrating the efficacy of preference-calibrated binary signals in modeling inter-user differences.</abstract>
<identifier type="citekey">ma-etal-2026-personalizing</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1222/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>26539</start>
<end>26555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework
%A Ma, Xilai
%A Zhao, Liye
%A Yao, Weijun
%A Di, Haibing
%A Wang, Wenya
%A Li, Jing
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F ma-etal-2026-personalizing
%X Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences.Existing methods often focus on isolated user histories, neglecting the essential role of inter-user differences.We propose C-BPO, a framework that personalizes LLMs via preference-calibrated binary signals.By treating target user data as positive feedback and other users’ data as an auxiliary set of implicit negative signals, C-BPO captures distinct inter-user differences.To mitigate the preference overlap issue, where shared task knowledge is erroneously penalized, we derive an objective grounded in Positive-Unlabeled (PU) learning theory.This approach purifies negative signals by subtracting “positive bias”, ensuring alignment with unique idiosyncrasies without compromising general helpfulness.Empirical experiments across various personalization tasks and backbone LLMs show C-BPO consistently outperforms baselines, demonstrating the efficacy of preference-calibrated binary signals in modeling inter-user differences.
%U https://aclanthology.org/2026.acl-long.1222/
%P 26539-26555
Markdown (Informal)
[Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework](https://aclanthology.org/2026.acl-long.1222/) (Ma et al., ACL 2026)
ACL