@inproceedings{gendron-etal-2026-conversational,
title = "Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation",
author = "Gendron, Barbara and
Guibon, Gael and
d{'}Aquin, Mathieu",
editor = "S{\'e}rasset, Gilles and
Gkirtzou, Katerina and
Cochez, Michael and
Kalo, Jan-Christoph",
booktitle = "Proceedings of the Knowledge Graphs and Large Language Models Workshop ({KG}-{LLM}) @ {LREC}26",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.kallm-1.3/",
doi = "10.63317/446x4ysrhfeq",
pages = "20--35",
abstract = "Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gendron-etal-2026-conversational">
<titleInfo>
<title>Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Gendron</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gael</namePart>
<namePart type="family">Guibon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">d’Aquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.</abstract>
<identifier type="citekey">gendron-etal-2026-conversational</identifier>
<identifier type="doi">10.63317/446x4ysrhfeq</identifier>
<location>
<url>https://aclanthology.org/2026.kallm-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>20</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation
%A Gendron, Barbara
%A Guibon, Gael
%A d’Aquin, Mathieu
%Y Sérasset, Gilles
%Y Gkirtzou, Katerina
%Y Cochez, Michael
%Y Kalo, Jan-Christoph
%S Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F gendron-etal-2026-conversational
%X Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.
%R 10.63317/446x4ysrhfeq
%U https://aclanthology.org/2026.kallm-1.3/
%U https://doi.org/10.63317/446x4ysrhfeq
%P 20-35
Markdown (Informal)
[Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation](https://aclanthology.org/2026.kallm-1.3/) (Gendron et al., KaLLM 2026)
ACL