@inproceedings{wang-etal-2026-self-guided,
title = "Self-Guided Alignment: Adaptive Preference {S}ensing for Multi-Objective Generation",
author = "Wang, Ning and
Liu, Zhanyang and
Zhou, Taotao and
Zhang, Xinrui and
Shao, Zongru and
Zhou, Haojie",
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.2184/",
pages = "47202--47220",
ISBN = "979-8-89176-390-6",
abstract = "Aligning Large Language Models (LLMs) with diverse and potentially conflicting human values necessitates navigating complex multi-objective landscapes. However, existing prompt-conditioned approaches face a critical training-inference discrepancy: they rely on ground-truth scores during training while requiring manual user-specification at inference. We introduce prediction of implicit preferences to bridge this gap while reducing user burden. To this end, we propose Self-Guided Alignment (SGA), a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability. It employs a dual-head architecture to unify preference internalization with conditional generation, enabling the model to learn a latent mapping between raw prompts and preference profiles. Through adaptive preference sensing, the model autonomously predicts the latent preference score to self-guide the generation, thereby eliminating the need for manual specification at inference. Extensive experiments across diverse model scales demonstrate that SGA often outperforms state-of-the-art baselines, achieving superior multi-objective trade-offs and improved preference alignment. Code is available at https://github.com/python-yyds/SGA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-self-guided">
<titleInfo>
<title>Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taotao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongru</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haojie</namePart>
<namePart type="family">Zhou</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>Aligning Large Language Models (LLMs) with diverse and potentially conflicting human values necessitates navigating complex multi-objective landscapes. However, existing prompt-conditioned approaches face a critical training-inference discrepancy: they rely on ground-truth scores during training while requiring manual user-specification at inference. We introduce prediction of implicit preferences to bridge this gap while reducing user burden. To this end, we propose Self-Guided Alignment (SGA), a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability. It employs a dual-head architecture to unify preference internalization with conditional generation, enabling the model to learn a latent mapping between raw prompts and preference profiles. Through adaptive preference sensing, the model autonomously predicts the latent preference score to self-guide the generation, thereby eliminating the need for manual specification at inference. Extensive experiments across diverse model scales demonstrate that SGA often outperforms state-of-the-art baselines, achieving superior multi-objective trade-offs and improved preference alignment. Code is available at https://github.com/python-yyds/SGA.</abstract>
<identifier type="citekey">wang-etal-2026-self-guided</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2184/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>47202</start>
<end>47220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation
%A Wang, Ning
%A Liu, Zhanyang
%A Zhou, Taotao
%A Zhang, Xinrui
%A Shao, Zongru
%A Zhou, Haojie
%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 wang-etal-2026-self-guided
%X Aligning Large Language Models (LLMs) with diverse and potentially conflicting human values necessitates navigating complex multi-objective landscapes. However, existing prompt-conditioned approaches face a critical training-inference discrepancy: they rely on ground-truth scores during training while requiring manual user-specification at inference. We introduce prediction of implicit preferences to bridge this gap while reducing user burden. To this end, we propose Self-Guided Alignment (SGA), a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability. It employs a dual-head architecture to unify preference internalization with conditional generation, enabling the model to learn a latent mapping between raw prompts and preference profiles. Through adaptive preference sensing, the model autonomously predicts the latent preference score to self-guide the generation, thereby eliminating the need for manual specification at inference. Extensive experiments across diverse model scales demonstrate that SGA often outperforms state-of-the-art baselines, achieving superior multi-objective trade-offs and improved preference alignment. Code is available at https://github.com/python-yyds/SGA.
%U https://aclanthology.org/2026.acl-long.2184/
%P 47202-47220
Markdown (Informal)
[Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation](https://aclanthology.org/2026.acl-long.2184/) (Wang et al., ACL 2026)
ACL