@inproceedings{poole-jahanbakhsh-2026-personalized,
title = "Personalized Alignment of Language Models with Human Value Profiles",
author = "Poole, Rashon and
Jahanbakhsh, Farnaz",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1600/",
pages = "36378--36403",
ISBN = "979-8-89176-459-0",
abstract = "Large language models are increasingly used for subjective tasks such as seeking advice, where there is often no single correct answer. Yet dominant alignment methods learn a single behavior policy that applies uniformly across users, limiting their ability to reflect individual value priorities. We propose personalized value alignment, a framework for adapting model responses to users' stable value profiles rather than to personas, demographics, or task-specific preferences used in prior personalization work. Our approach represents users through Schwartz value profiles and selects which of their values are relevant to each query before applying targeted prompting, activation steering, or LoRA-DPO. We create a dataset of 1,501 value-tension scenarios and evaluate over 152 diverse value profiles sampled from a nationally representative survey. Value-targeted methods outperform no-personalization, demographic, and full-profile prompting baselines, indicating that gains come from focused conditioning on query-specific value priorities rather than mere exposure. We further find that steering effects are not uniform across users: alignment gains vary by where a user{'}s priorities fall in the value space. Combining targeted prompting with activation steering or LoRA-DPO yields the strongest personalization while keeping logical quality within adequate range."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poole-jahanbakhsh-2026-personalized">
<titleInfo>
<title>Personalized Alignment of Language Models with Human Value Profiles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rashon</namePart>
<namePart type="family">Poole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farnaz</namePart>
<namePart type="family">Jahanbakhsh</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large language models are increasingly used for subjective tasks such as seeking advice, where there is often no single correct answer. Yet dominant alignment methods learn a single behavior policy that applies uniformly across users, limiting their ability to reflect individual value priorities. We propose personalized value alignment, a framework for adapting model responses to users’ stable value profiles rather than to personas, demographics, or task-specific preferences used in prior personalization work. Our approach represents users through Schwartz value profiles and selects which of their values are relevant to each query before applying targeted prompting, activation steering, or LoRA-DPO. We create a dataset of 1,501 value-tension scenarios and evaluate over 152 diverse value profiles sampled from a nationally representative survey. Value-targeted methods outperform no-personalization, demographic, and full-profile prompting baselines, indicating that gains come from focused conditioning on query-specific value priorities rather than mere exposure. We further find that steering effects are not uniform across users: alignment gains vary by where a user’s priorities fall in the value space. Combining targeted prompting with activation steering or LoRA-DPO yields the strongest personalization while keeping logical quality within adequate range.</abstract>
<identifier type="citekey">poole-jahanbakhsh-2026-personalized</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1600/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36378</start>
<end>36403</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalized Alignment of Language Models with Human Value Profiles
%A Poole, Rashon
%A Jahanbakhsh, Farnaz
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F poole-jahanbakhsh-2026-personalized
%X Large language models are increasingly used for subjective tasks such as seeking advice, where there is often no single correct answer. Yet dominant alignment methods learn a single behavior policy that applies uniformly across users, limiting their ability to reflect individual value priorities. We propose personalized value alignment, a framework for adapting model responses to users’ stable value profiles rather than to personas, demographics, or task-specific preferences used in prior personalization work. Our approach represents users through Schwartz value profiles and selects which of their values are relevant to each query before applying targeted prompting, activation steering, or LoRA-DPO. We create a dataset of 1,501 value-tension scenarios and evaluate over 152 diverse value profiles sampled from a nationally representative survey. Value-targeted methods outperform no-personalization, demographic, and full-profile prompting baselines, indicating that gains come from focused conditioning on query-specific value priorities rather than mere exposure. We further find that steering effects are not uniform across users: alignment gains vary by where a user’s priorities fall in the value space. Combining targeted prompting with activation steering or LoRA-DPO yields the strongest personalization while keeping logical quality within adequate range.
%U https://aclanthology.org/2026.emnlp-main.1600/
%P 36378-36403
Markdown (Informal)
[Personalized Alignment of Language Models with Human Value Profiles](https://aclanthology.org/2026.emnlp-main.1600/) (Poole & Jahanbakhsh, EMNLP 2026)
ACL