@inproceedings{li-etal-2026-extended,
title = "Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals",
author = "Li, Jia-Nan and
Guan, Jian and
Wu, Wei and
Yan, Rui",
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.718/",
pages = "16650--16682",
ISBN = "979-8-89176-459-0",
abstract = "While large language models (LLMs) excel at deductive reasoning tasks such as math and coding, their capacity for inductive reasoning remains underexplored. This paper investigates this through the lens of personalized preference inference, where models must synthesize consistent patterns from implicit behavioral signals in users' interaction histories. We propose AlignXplore, a model that leverages extended reasoning chains to enable explicit preference inference. Such explicit articulation enables an efficient streaming inference mechanism, allowing the model to incrementally refine preference descriptions without reprocessing historical signals. Guided by a specialized reward modeling strategy, we develop AlignXplore by combining synthetic-data cold-start training with online reinforcement learning. Extensive experiments show AlignXplore outperforms the backbone model by 15.49{\%} on average across in- and out-of-domain benchmarks, while exhibiting robust generalization to diverse input formats and downstream models. Our analysis further establishes reward modeling best practices and reveals the emergence of human-like inductive reasoning patterns during training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-extended">
<titleInfo>
<title>Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia-Nan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</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>While large language models (LLMs) excel at deductive reasoning tasks such as math and coding, their capacity for inductive reasoning remains underexplored. This paper investigates this through the lens of personalized preference inference, where models must synthesize consistent patterns from implicit behavioral signals in users’ interaction histories. We propose AlignXplore, a model that leverages extended reasoning chains to enable explicit preference inference. Such explicit articulation enables an efficient streaming inference mechanism, allowing the model to incrementally refine preference descriptions without reprocessing historical signals. Guided by a specialized reward modeling strategy, we develop AlignXplore by combining synthetic-data cold-start training with online reinforcement learning. Extensive experiments show AlignXplore outperforms the backbone model by 15.49% on average across in- and out-of-domain benchmarks, while exhibiting robust generalization to diverse input formats and downstream models. Our analysis further establishes reward modeling best practices and reveals the emergence of human-like inductive reasoning patterns during training.</abstract>
<identifier type="citekey">li-etal-2026-extended</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.718/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>16650</start>
<end>16682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
%A Li, Jia-Nan
%A Guan, Jian
%A Wu, Wei
%A Yan, Rui
%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 li-etal-2026-extended
%X While large language models (LLMs) excel at deductive reasoning tasks such as math and coding, their capacity for inductive reasoning remains underexplored. This paper investigates this through the lens of personalized preference inference, where models must synthesize consistent patterns from implicit behavioral signals in users’ interaction histories. We propose AlignXplore, a model that leverages extended reasoning chains to enable explicit preference inference. Such explicit articulation enables an efficient streaming inference mechanism, allowing the model to incrementally refine preference descriptions without reprocessing historical signals. Guided by a specialized reward modeling strategy, we develop AlignXplore by combining synthetic-data cold-start training with online reinforcement learning. Extensive experiments show AlignXplore outperforms the backbone model by 15.49% on average across in- and out-of-domain benchmarks, while exhibiting robust generalization to diverse input formats and downstream models. Our analysis further establishes reward modeling best practices and reveals the emergence of human-like inductive reasoning patterns during training.
%U https://aclanthology.org/2026.emnlp-main.718/
%P 16650-16682
Markdown (Informal)
[Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals](https://aclanthology.org/2026.emnlp-main.718/) (Li et al., EMNLP 2026)
ACL