@inproceedings{proietti-etal-2026-mechanistic,
title = "Mechanistic Interpretability Meets Cognitive Linguistics: Modelling Locative Image Schemas in the Circuit Framework",
author = "Proietti, Mattia and
Alishahi, Afra and
Chrupa{\l}a, Grzegorz and
Lenci, Alessandro",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.885/",
doi = "10.63317/4iwnnycar4sc",
pages = "11320--11331",
abstract = "Large Language Models are often considered the best computational testbeds for linguistic theorisation at our disposal. However, their inner workings remain largely opaque, and the mechanisms behind their behaviour cannot always be easily connected with theoretical linguistic assumptions. Mechanistic Interpretability (MI) is surging as a specialised field to reverse engineer models' internals and shed light on the causal relationships happening under the hood. Nevertheless, MI is predominantly focused on AI-Safety problems, and the attempts to understand linguistically motivated behaviours with these tools are still limited. In this work, we investigate whether an LLM, namely LlaMA-3.2-1b, has developed specialised mechanisms governing the selection of the locative preposition in simple copular clauses. To frame the problem as a next-token prediction objective, we introduce the Stranded Locative Preposition Selection task along with a small dataset aptly curated to test it. We make use of several MI tools to scan the model{'}s internals and relate their mechanisms to classic theory in Cognitive Linguistics, which assumes that the two basic locative prepositions in and on are the respective linguistic encoding of two different Image Schemas: Containment and Surface"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="proietti-etal-2026-mechanistic">
<titleInfo>
<title>Mechanistic Interpretability Meets Cognitive Linguistics: Modelling Locative Image Schemas in the Circuit Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="family">Proietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Alishahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models are often considered the best computational testbeds for linguistic theorisation at our disposal. However, their inner workings remain largely opaque, and the mechanisms behind their behaviour cannot always be easily connected with theoretical linguistic assumptions. Mechanistic Interpretability (MI) is surging as a specialised field to reverse engineer models’ internals and shed light on the causal relationships happening under the hood. Nevertheless, MI is predominantly focused on AI-Safety problems, and the attempts to understand linguistically motivated behaviours with these tools are still limited. In this work, we investigate whether an LLM, namely LlaMA-3.2-1b, has developed specialised mechanisms governing the selection of the locative preposition in simple copular clauses. To frame the problem as a next-token prediction objective, we introduce the Stranded Locative Preposition Selection task along with a small dataset aptly curated to test it. We make use of several MI tools to scan the model’s internals and relate their mechanisms to classic theory in Cognitive Linguistics, which assumes that the two basic locative prepositions in and on are the respective linguistic encoding of two different Image Schemas: Containment and Surface</abstract>
<identifier type="citekey">proietti-etal-2026-mechanistic</identifier>
<identifier type="doi">10.63317/4iwnnycar4sc</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.885/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11320</start>
<end>11331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mechanistic Interpretability Meets Cognitive Linguistics: Modelling Locative Image Schemas in the Circuit Framework
%A Proietti, Mattia
%A Alishahi, Afra
%A Chrupała, Grzegorz
%A Lenci, Alessandro
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F proietti-etal-2026-mechanistic
%X Large Language Models are often considered the best computational testbeds for linguistic theorisation at our disposal. However, their inner workings remain largely opaque, and the mechanisms behind their behaviour cannot always be easily connected with theoretical linguistic assumptions. Mechanistic Interpretability (MI) is surging as a specialised field to reverse engineer models’ internals and shed light on the causal relationships happening under the hood. Nevertheless, MI is predominantly focused on AI-Safety problems, and the attempts to understand linguistically motivated behaviours with these tools are still limited. In this work, we investigate whether an LLM, namely LlaMA-3.2-1b, has developed specialised mechanisms governing the selection of the locative preposition in simple copular clauses. To frame the problem as a next-token prediction objective, we introduce the Stranded Locative Preposition Selection task along with a small dataset aptly curated to test it. We make use of several MI tools to scan the model’s internals and relate their mechanisms to classic theory in Cognitive Linguistics, which assumes that the two basic locative prepositions in and on are the respective linguistic encoding of two different Image Schemas: Containment and Surface
%R 10.63317/4iwnnycar4sc
%U https://aclanthology.org/2026.lrec-1.885/
%U https://doi.org/10.63317/4iwnnycar4sc
%P 11320-11331
Markdown (Informal)
[Mechanistic Interpretability Meets Cognitive Linguistics: Modelling Locative Image Schemas in the Circuit Framework](https://aclanthology.org/2026.lrec-1.885/) (Proietti et al., LREC 2026)
ACL