@inproceedings{khan-etal-2026-stoicllm,
title = "{S}toic{LLM}: Preference Optimization for Philosophical Alignment in Small Language Models",
author = "Khan, Ishmam and
Thogarrati, Sindhuja and
Zhang, Shuo",
editor = {Hamilton, Sil and
{\"O}hman, Emily and
Hicke, Rebecca M. M. and
Bizzoni, Yuri and
Bax, Axel and
Matthews, Jacob A. and
H{\"a}m{\"a}l{\"a}inen, Mika},
booktitle = "Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities",
month = jul,
year = "2026",
address = "San Diego, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4dh-1.32/",
pages = "355--367",
ISBN = "979-8-89176-427-9",
abstract = "While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints remains underexplored. We investigate this by specializing small LLMs on micro-datasets of foundational Stoic texts using preference optimization (ORPO, AlphaPO). Evaluated via a multi-model critic bank, our results show that just 300 high-fidelity examples can induce strong alignment with inward-facing Stoic virtues, closely approaching few-shot prompting while freeing the context window. Critically, however, all models, including few-shot baselines, exhibit a persistent failure on Stoicism{'}s outward-facing cosmopolitan duties, pointing to a representational limitation of small models that micro-dataset adaptation alone cannot overcome."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khan-etal-2026-stoicllm">
<titleInfo>
<title>StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ishmam</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sindhuja</namePart>
<namePart type="family">Thogarrati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Zhang</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 6th International Conference on Natural Language Processing for the Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sil</namePart>
<namePart type="family">Hamilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="given">M</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Hicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="family">Bax</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Matthews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-427-9</identifier>
</relatedItem>
<abstract>While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints remains underexplored. We investigate this by specializing small LLMs on micro-datasets of foundational Stoic texts using preference optimization (ORPO, AlphaPO). Evaluated via a multi-model critic bank, our results show that just 300 high-fidelity examples can induce strong alignment with inward-facing Stoic virtues, closely approaching few-shot prompting while freeing the context window. Critically, however, all models, including few-shot baselines, exhibit a persistent failure on Stoicism’s outward-facing cosmopolitan duties, pointing to a representational limitation of small models that micro-dataset adaptation alone cannot overcome.</abstract>
<identifier type="citekey">khan-etal-2026-stoicllm</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4dh-1.32/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>355</start>
<end>367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
%A Khan, Ishmam
%A Thogarrati, Sindhuja
%A Zhang, Shuo
%Y Hamilton, Sil
%Y Öhman, Emily
%Y Hicke, Rebecca M. M.
%Y Bizzoni, Yuri
%Y Bax, Axel
%Y Matthews, Jacob A.
%Y Hämäläinen, Mika
%S Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA
%@ 979-8-89176-427-9
%F khan-etal-2026-stoicllm
%X While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints remains underexplored. We investigate this by specializing small LLMs on micro-datasets of foundational Stoic texts using preference optimization (ORPO, AlphaPO). Evaluated via a multi-model critic bank, our results show that just 300 high-fidelity examples can induce strong alignment with inward-facing Stoic virtues, closely approaching few-shot prompting while freeing the context window. Critically, however, all models, including few-shot baselines, exhibit a persistent failure on Stoicism’s outward-facing cosmopolitan duties, pointing to a representational limitation of small models that micro-dataset adaptation alone cannot overcome.
%U https://aclanthology.org/2026.nlp4dh-1.32/
%P 355-367
Markdown (Informal)
[StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models](https://aclanthology.org/2026.nlp4dh-1.32/) (Khan et al., NLP4DH 2026)
ACL